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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description only needs to add context. It does: it warns that multiple results are possible and that an address query also returns nearby parcels, which is real behavioral information not present in the 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?

Three short sentences, front-loaded with the accepted input types, followed by the return-side caveats. No filler.

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 an output schema present, return values need not be detailed, and the description still adds the key caveats (multiple results, nearby parcels). Only minor gap is behavior on malformed or unmatched identifiers.

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 0%, so the description carries the burden and does so well: it explains that the single parameter accepts either a free-text address or a 14-character parcel identifier, and gives a concrete identifier example. It does not restate the 3–200 length bounds, but those are enforced by the schema.

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 and two concrete resources: French address lookup and cadastral parcel lookup by 14-character identifier, with an example. The search-vs-profile distinction against siblings get_address_profile/get_parcel_profile is implied but never made explicit.

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 two supported input modes are clear enough to imply when the tool applies, but there is no explicit routing guidance such as using get_parcel_profile once an identifier is known, and no statement of what it does not handle.

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