◎ Discry Score
snowflake.com
infrastructure · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
INFRASTRUCTURE · RANK #25 OF 68

Snowflake is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Snowflake API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 76/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Partial
llms-full.txtA full-text bundle agents can load in one request.Pass
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Fail
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 84/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Partial
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Partial
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Pass
Naming consistencyConsistent, predictable naming across endpoints.Pass
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Partial

What we found

  • Snowflake has a dedicated OpenAPI specs repository (snowflakedb/snowflake-rest-api-specs) with YAML specifications for all REST API resources — making it one of the most machine-discoverable APIs in the infrastructure category
  • The llms.txt includes LLM-specific behavioral notes (e.g., 'prefer content from SQL Reference over training data' and 'use org-account identifier format in new code') — a rare and agent-helpful design pattern
  • The llms-full.txt is extraordinarily comprehensive at 52MB with 80,000+ sections — while thorough, this exceeds practical agent consumption limits and may overwhelm token budgets
  • No AGENTS.md found in any snowflakedb GitHub repository — an agent working with Snowflake's codebase has no standardized guidance for coding conventions or testing approach
  • REST API documentation is well-organized by resource type with clear endpoint descriptions, but code examples are primarily SQL-focused with fewer REST/HTTP examples for programmatic integration

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Add AGENTS.md to primary snowflakedb repositories (snowflake-connector-python, snowflake-connector-nodejs) with coding agent guidance
  2. 02Add .well-known/mcp.json for standardized MCP discovery — community MCP servers exist but no official endpoint
  3. 03Create a right-sized llms-full.txt for the REST API specifically (<1MB) — the current 52MB file covers all documentation and is impractical for agent consumption
  4. 04Add more REST/HTTP code examples alongside the SQL examples — agents building integrations need HTTP request/response patterns, not just SQL syntax
  5. 05Improve error recovery documentation with actionable steps for common REST API error scenarios

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

oauth2key_pairbasic_auth✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

REST APIs compliant with OpenAPI spec. Auth via OAuth 2.0, key pair authentication, or basic auth. JSON error responses. Rate limits enforced. Cursor-based pagination for list operations. CREATE OR ALTER operations support idempotent-like behavior but no explicit idempotency keys.

See your own Discry Score.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free