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

Annotations already cover the safety profile (readOnly, openWorld, idempotent, non-destructive), so the description is free to add operational context it does add: it returns multiple candidates with category/commune/coordinates, and warns that the first candidate is not always correct (a 'Gare' neighbourhood is not the station). It does not mention rate limits or result-ordering logic, but the verification warning is genuinely useful behavioral guidance.

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?

Front-loads the core purpose and the workflow, then moves to query guidance and the category/commune warning. Every sentence carries information, though the two examples and the verification caveat make it longer than strictly necessary.

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?

For a two-parameter read-only geocoder with no output schema, the description supplies everything needed: what it returns (candidates with category, commune, coordinates), how to feed the result forward, and the ambiguity risk to watch for. Nothing material is missing.

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 description coverage is 100%, so the baseline is 3, but the description goes further by prescribing query composition ('Inclure la commune dans la requête et le nom officiel') with concrete examples such as 'gare Angers Saint-Laud'. It adds meaning beyond the schema's short example, though it says nothing about the limit parameter's trade-off.

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?

Opens with a specific verb+resource ('Géocode un lieu nommé') and enumerates the POI types it covers (gare, mairie, hôpital, école, monument, station de tram), backed by the IGN index. It explicitly contrasts itself with address/street/place lookups, which use the address parameter of the search tools, so an agent can separate it from siblings like find_parcelles_by_address.

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?

States the downstream workflow ('Passer ensuite lat et lng du bon candidat à search_dpe, search_ventes_dvf ou search_parcelles') and names the exclusion condition: for an address, street or place, use the address parameter of the search tools instead. Both when-to-use and when-not-to-use are explicit.

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