Robin Saige we check the tools AI agents call

SeaWeb

tech.seaweb/seaweb

Agent-native search: SF travel + restaurants. Honest labels; partner-confirmed request relay.

— the operator's own registry description reported

Publisher tech.seaweb · first seen 2026-08-12 · endpoint https://api.seaweb.tech/mcp

allow
verdict
rich-slow-solo
cluster
ok_tools
answers
38
tools served

Dependency rating derived

allow
allow — alive & usable · retrieval-public ● · V3 has answer key ◐
allow — because answers ●, 38 tools legible (band B) ●, no confirmed drift in 3 probes ●; not yet checked: truth (2 attempts unverifiable, 0 disagreements)

Cluster rich-slow-solo · distinctiveness 0.915 (unusual). Every figure is a percentile or class within the 11,363-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency1164 ms
vs populationslow
protocolcurrent
authopen
Can it be used? Q4 · observed
tools38
vs populationhigh
capabilities4
harnessB
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true0/0 agree

🔏 Signed receipt rr_eb8d3add3f80bd2a27ebd982 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Q1Does it answer?alive & usable — 3 probes ●evidence ↓
Q2What is it?retrieval-public ● evidence ↓
Q3Can it be checked?V3 has answer key ◐evidence ↓
Q4Did it hold?harness B · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?rich-slow-solo · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (3 shown, 2026-08-12 → 2026-08-16). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (3 events)
datetypewhat changed
2026-08-16outcomeok_tools (was connect_error)
2026-08-14outcomeconnect_error (was auth_required)
2026-08-12outcomefirst probe: auth_required

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
retrieval-public24serves public factstruth-checkable against a public source — the V-ladder applies in full
action7changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
generative3creates contentno answer key exists; disclosure + stability checks, never truth verdicts
computational2deterministic transformsself-checkable by re-computation and known-answer tests
orchestration1routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)
predictive1claims about the futurescoreable only in retrospect — the archive scores yesterday's predictions against today's outcome

Tools last seen observed

compare_search delete_disruption_webhook delete_standing_query extract_url filter_restaurants filter_salons get_details get_disruption_event get_disruptions get_entity get_hours get_menu get_restaurant get_salon get_services get_site_skill list_disruption_events list_disruption_webhooks list_sources list_standing_queries list_verticals log_outcome recall register_disruption_webhook register_standing_query remember research research_status resolve_geo search search_destination_sentiment search_restaurants search_salons search_web submit_feedback teamwork_preview travel_health vote_comparison

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band B — usable, with rough edges.

legibility checktools passingok
name is clear & specific38/38
has a description38/38
description is substantive38/38
parameters are typed38/38
parameters are described4/384/38

38 of 38 tools graded · 38 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not yet confirmed — 2 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim classkeyverdictprimary source
tariff-duty0901.21.00unverifiableus-hts
tariff-duty6109.10.00unverifiableus-hts

Protocol conformance observed

2025-06-18
protocol version
session model
1.29.0
server version SeaWeb

Capabilities: experimental prompts resources tools

Drift observed

No confirmed drift on record. Baseline set 2026-08-16; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-16T06:14:22Zok_tools20011642025-06-18
2026-08-14T20:00:46Zconnect_error178
2026-08-12T05:35:59Zauth_required401995

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/tech.seaweb/seaweb.svg)](https://robinsaige.com/s/tech.seaweb/seaweb)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →