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

The annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds meaningful context by stating 'Lecture seule' and, more importantly, that the result is indicative and that manufacturer technical notices take precedence. This is useful behavioral disclosure beyond structured fields, though return format is not described.

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 dense but front-loaded with the call condition and purpose before moving into structural details. Every clause carries domain-specific information, with no filler sentences. It is slightly repetitive in restating the 'scene' structure already in the schema, but overall efficient.

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 tool with one nested object parameter and no output schema, the description gives enough context to call it correctly: the required scene shape, the classification thresholds, and the indicative nature of the result. It does not describe what the return value looks like (e.g., conformity verdict per element), which is a minor gap but not blocking for invocation.

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 substantial meaning beyond the schema's generic summary. It spells out the nested structure of 'scene.menuiseries_aev' with fields (element, exposition, classement, pose) and gives example exposure/classement values and threshold logic (A2E3V2 for faible, A3E5V2 for moderee, A4E6V3 for forte), which an agent could not infer from the schema alone.

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 opens with a specific trigger and verb: 'Appelez quand vous devez verifier le CLASSEMENT AEV des menuiseries (NF DTU 36.5)'. It names the exact resource (menuiseries), the regulatory framework (NF DTU 36.5), and the classification dimensions (air/eau/vent), which clearly distinguishes it from siblings like cao_bim_vitrages or cao_bim_etancheite.

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 phrase 'Appelez quand vous devez verifier...' gives explicit when-to-use guidance. It also includes a caveat that the result is 'Indicatif — avis techniques fabricants priment', which helps the agent understand the tool's role. It does not name an alternative sibling tool for related checks, so it falls short of a 5.

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