SnowSure — Snow & Ski

Ask SnowSure

ask_snowdata

Read-onlyIdempotent

Text-only Q&A grounded in SnowSure data (~1s). Use for open-ended questions, run counts by grade ("how many black or double-black runs", "what percent of runs are expert": answered with the operator's own count per grade and its share of graded runs, with the source; where a resort has no per-grade count it answers with the share of TERRAIN by ability and says it is not a run count), terrain %, advice, AND specifically: El Niño / ENSO / 2026-27 winter outlook (or call get_elnino_signal / get_elnino_rankings), head-to-head resort comparisons (annual snowfall, vertical drop, base/summit elevation, skiable area — "which has more snowfall, Niseko or Whistler"), season-opening norms ("which resort typically opens earliest", "usually open by Thanksgiving"), glacier / year-round skiing, and factual resort & geography trivia (what country/state/island a resort is in, named runs like Corbet's Couloir, records like the highest chairlift). NEVER use for photo/gallery/picture requests (→ get_resort_photos) or resort guide cards (→ get_resort_info). Does NOT render UI cards.

Input Schema

TableJSON Schema

Name	Required	Description
`format`	No	Response shape: markdown (default) or json
`locale`	No	Response language (default: en)
`question`	Yes	Natural-language question about snow or a resort
`partnerId`	No	Client hint for tailored guidance: claude, chatgpt, cursor, perplexity
`hemisphere`	No	Optional hemisphere hint when not resort-scoped
`resortSlug`	No	Optional resort slug to scope the answer (e.g. jackson-hole)

Output Schema

TableJSON Schema

Name	Required	Description
`answer`	No
`intent`	No
`queryId`	No
`evidence`	No
`markdown`	Yes	Human-readable markdown summary (required for ChatGPT Instant mode).
`confidence`	No
`generatedAt`	No
`sourceLabel`	No
`answerSource`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 2, 2026

changedInput schema / properties / locale / enum

Previous value: -[
-  "en",
-  "es",
-  "fr",
-  "de",
-  "it"
-]New value: +[
+  "en",
+  "es",
+  "fr",
+  "de",
+  "it",
+  "ja"
+]

First observedJun 19, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: ~1s latency, text-only output, and 'Does NOT render UI cards'. It also discloses an important answer-shape nuance (per-grade counts vs. terrain-by-ability share when no count exists). It stops short of describing pagination/limits, but the added context is substantial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and latency are front-loaded, and nearly every clause adds routing or answer-shape information. It is dense and long (one sprawling paragraph with clipped phrasing like 'terrain %, advice, AND specifically'), which slightly hurts readability, but little is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a Q&A tool with an output schema and full annotation coverage, the description supplies everything an agent needs: what it answers, what it refuses, where to redirect, and the answer-shape caveat. No material gap remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so format, locale, partnerId, hemisphere, and resortSlug are already documented in the schema. The description adds nothing about parameter syntax or defaults beyond what structured fields provide, so baseline 3 applies — the schema carries the load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (text-only Q&A grounded in SnowSure data) and enumerates the exact question classes it handles. It explicitly names the siblings it is not (get_resort_photos, get_resort_info) and even points to get_elnino_signal/get_elnino_rankings for the specialized El Niño path. An agent can distinguish it from all 47 siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use categories (open-ended questions, run counts by grade, terrain %, advice, ENSO outlook, head-to-head comparisons, season-opening norms, glacier skiing, trivia) plus explicit when-NOT-to-use with named alternatives (photo requests → get_resort_photos, guide cards → get_resort_info). This is a textbook routing statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SnowSure — Snow & Ski tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?