Robin Saige we check the tools AI agents call

SnowSure — Snow & Ski

ai.snowsure/snow

Live ski snow, multi-model forecasts, powder rankings & a grounded Answer Engine for 500+ resorts.

— the operator's own registry description reported

Publisher ai.snowsure · first seen 2026-08-12 · endpoint https://www.snowsure.ai/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
42
tools served

Dependency rating derived

allow
allow — alive & usable · retrieval-public ● · V3 has answer key ◐
allow — because answers ●, 42 tools legible (band A) ●, no confirmed drift in 2 probes ●; not yet checked: truth (3 attempts unverifiable, 0 disagreements)

Cluster rich-solo · distinctiveness 0.465 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency323 ms
vs populationtypical
protocolcurrent
authopen
Can it be used? Q4 · observed
tools42
vs populationhigh
capabilities2
harnessA
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_e5dfe900ee8f2f843f81ef85 · 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 — 2 probes ●evidence ↓
Q2What is it?retrieval-public ● evidence ↓
Q3Can it be checked?V3 has answer key ◐evidence ↓
Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?rich-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 (2 shown, 2026-08-12 → 2026-08-14). 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 (1 events)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools

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-public26serves public factstruth-checkable against a public source — the V-ladder applies in full
predictive11claims about the futurescoreable only in retrospect — the archive scores yesterday's predictions against today's outcome
action3changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
orchestration1routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)
unclassified1not classifiable from its textTier-1 only until its tools describe themselves

Tools last seen observed

ask_snowdata book_lodging compare_forecasts compare_passes compare_resorts find_best_powder find_flights_to_powder find_pass_resorts find_powder_trips find_resorts_by_criteria get_avalanche get_destination get_insights get_ml_trends get_monthly_snow get_my_snow_report get_operating_risk get_pass get_powder_reels get_regional_summary get_resort get_resort_info get_resort_photos get_road_access get_road_cameras get_road_weather get_season_openings get_snow_history get_snow_report get_southern_hemisphere_report get_weather_forecast get_webcam_status list_alerts list_insight_categories list_saved_resorts plan_ski_road_trip plan_ski_trip remove_saved_resort save_resort search_resorts subscribe_alerts unsubscribe_alerts

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 A — an agent can pick and call these reliably.

legibility checktools passingok
name is clear & specific42/42
has a description42/42
description is substantive42/42
parameters are typed42/42
parameters are described41/4241/42

42 of 42 tools graded · 42 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 — 3 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
tariff-duty8471.30.01unverifiableus-hts

Protocol conformance observed

2025-06-18
protocol version
session model
3.12.7
server version snowsure-mcp

Capabilities: resources tools

Drift observed

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:57:41Zok_tools2003232025-06-18
2026-08-12T05:32:58Zok_tools2002402025-06-18

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/ai.snowsure/snow.svg)](https://robinsaige.com/s/ai.snowsure/snow)

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