rpps_dans_etablissement

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

Beyond annotations (readOnly, idempotent, openWorld), the description adds significant behavioral context: default filtering to Civil category, coverage limitations (only declared links), data staleness via include_freshness with caching details, and source attribution. No contradictions 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 length but well-organized: starts with purpose and scope, then explains default behavior and optional flags, covers data coverage and sources. Every sentence is informative, no redundancy, and the structure aids quick comprehension despite its length.

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 5 parameters and output schema existence, the description covers all critical aspects: core functionality with a concrete question, parameter details and defaults, data coverage and limitations, source and licensing, caching and freshness. It is complete enough for an agent to invoke correctly.

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?

With schema description coverage at only 20% (only include_freshness described in schema), the description provides detailed meaning for num_finess (9-digit pattern), include_agents_publics (examples like PH titulaires, médecins inspecteurs), and include_etudiants (internes, externes, élèves IDE/SF), including percentage breakdowns. The limit parameter lacks explanation, but overall the description substantially enhances understanding.

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 the tool lists healthcare professionals by FINESS establishment number, explicitly describing it as the 'RPPS↔FINESS pivot' and answering 'who works in this lab/hospital/clinic?'. This distinctly sets it apart from sibling tools like professionnel_by_rpps or etablissement_by_finess.

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 explains when to use the tool (having a FINESS number and needing professionals) and details parameter behavior (default Civil category, how to include agents publics and étudiants). It implicitly contrasts with other tools through its specific purpose, though it does not explicitly name alternatives or state when not to use it.

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