inspect_site

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

Annotations indicate read-only, non-destructive, idempotent, open-world. The description adds significant behavioral detail: parallel sub-calls, caching, payload size (~7K tokens), behavior when FINESS not found (returns specific structure), and the fact that historique may be unavailable. No contradiction with annotations.

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

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

The description is well-structured with sections (purpose, usage, format, cost, aliases). It is relatively long but each part serves a purpose (e.g., cost/payload details are relevant for selection). Could be slightly trimmed, but not excessive.

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

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

Given the tool's complexity (3 parameters, output schema, multiple sub-calls, caching), the description covers all necessary aspects: return format, error cases, aliases, performance considerations, and usage examples. No gaps identified.

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

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

Schema coverage is 100% with descriptions. The description adds meaning: for 'rpps_limit' it explains that 'professionnels.count' equals the sample size and 'truncated' flags excess; for 'historique_detail' it clarifies payload reduction. This exceeds the baseline of 3 for high coverage.

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

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

The description clearly states 'Vue 360 d'un établissement de santé en 1 appel' and explicitly names the three individual MCP calls it replaces. It identifies the tool as an aggregator that combines FINESS, SIRENE, RPPS, and INSEE data into a single call, distinguishing it from sibling tools.

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

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

The description explicitly lists use cases: prospection, audit territorial, batch CRM enrichment. It also advises when not to use it: 'Pour les besoins ciblés (juste le verdict, juste l'historique), préférer les tools individuels.' This provides clear when-to and when-not-to guidance with references to alternatives.

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