profil_iris

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

Annotations already indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds valuable behavioral context: data sources (INSEE RP 2022, FILOSOFI 2021), geographical limitations (hors métropole/en mer), return structure (LookupResult discriminated by found), and details about the revenue median being a proxy in aggregated mode. No contradiction 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 well-structured, starting with the purpose, then explaining the two modes, parameter constraints, data sources, and output details. Every sentence serves a purpose and adds value. Despite being long, it is concise for the complexity involved, with no redundant or irrelevant information.

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 the tool's complexity (two modes, proxy revenue, coverage limitations), the description is complete. It explains the proxy nature of revenue median, the coverage condition (FILOSOFI only for communes ≥5000 hab), output structure (LookupResult with found, mode, population, etc.), and data sources. Output schema exists, so return values are covered. No gaps remain.

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?

Although input schema coverage is 100% with parameter descriptions, the description clarifies the relationship between parameters (e.g., exactly one of point or code_iris) and the behavior of rayon_km (optional, range 0<r≤10, triggers basin mode). It also explains the meaning of code_iris format (9 car.) and the consequences of parameter choices, adding significant meaning beyond 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?

The description clearly states the tool provides demographic profiles at the IRIS level, with two distinct modes (single IRIS and aggregated basin). It distinguishes from the sibling tool 'population' by explicitly noting that for simple commune/department population, one should use 'population' instead.

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 provides explicit usage guidelines: it specifies that exactly one of point (lat+lon) or code_iris must be provided, and optionally rayon_km. It explains the two modes triggered by the presence or absence of rayon_km and tells when not to use this tool ('Pour une simple population de commune/dept, utiliser `population`').

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