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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial domain behavior: the reply lists the CCAM acts summed so matches can be verified, add-on codes and pathology are excluded from text matches, and a minimum-stay suppression rule applies. This is well beyond what annotations or schema convey.

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?

Dense but front-loaded with the core purpose, and nearly every sentence carries usable constraint or routing information. It is longer than typical and could be tightened, but there is little filler to cut.

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?

With no output schema, the description compensates by explaining what the reply contains (ranked sites plus the CCAM acts aggregated), the geographic default, and the follow-up path for surgeon-level questions. An agent has everything needed to call this 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantics: procedure accepts English or French free text or CCAM codes with examples and an 8th phase digit dropped, and place accepts city/postcode/arrondissement/département/FINESS with 'without place it ranks all of France' default behavior.

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?

States a specific verb+resource with scope: which French hospitals/clinics perform a procedure most, sourced from Open CCAM (ATIH), 2021-2025. It is clearly distinct from the sibling doctor-lookup tools and even states the boundary ('Hospital-level only: it does not say which surgeon operates').

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?

Explicitly says what is and isn't counted (PMSI MCO stays/day cases; office and outpatient clinics excluded; sites under 11 stays suppressed) and when to use the alternative ('Then use search_doctors with hospital_finess ... or with the hospital's postcode and the specialty'). It also tells the agent to disambiguate vague terms like 'aneurysm'/'stent' by site.

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