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

Annotations already declare readOnly/openWorld/idempotent behavior, and the description adds meaningful context: it returns the 500 most recent records and states that the API paginates the rest, while noting the data comes from commune declarations to the ministry. This is valuable beyond the annotations, though pagination mechanics are not detailed.

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 a single dense sentence that front-loads the permit types, then lists the returned fields, data source, and pagination limit. Every clause adds information, though breaking it into shorter sentences or bullets would improve scannability.

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 carries the full burden of explaining return content, and it lists all relevant fields (date, nature, address, parcel, housing/surface, status, applicant if legal entity). It also covers the key behavioral constraint of the 500-record limit and pagination, making the tool complete for a single-parameter read-only query.

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?

The single parameter code_insee is already fully documented in the schema with a pattern and an example (94081 Vitry-sur-Seine), and schema coverage is 100%. The description adds no parameter-specific detail, but that is unnecessary at this coverage level.

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 names a specific resource: building, development, demolition permits and prior declarations in a French commune, with a precise data source (Sitadel) and field list. This clearly differentiates it from the sibling tools (address facts, commune facts, parcel), which cover different data domains.

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 gives clear context for when to use the tool: any time permit/urbanism authorization data for a commune is needed, keyed by code_insee. It does not explicitly name alternatives or exclusions, but the resource is distinct enough from the siblings that no comparison is needed.

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