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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered; 'Lecture seule' merely repeats it. The description does add a genuinely useful behavioral caveat — 'Indicatif — DTU 20.12 signe prime' — telling the agent the verdict is advisory and may be overridden by the signed standard, which is context annotations cannot provide.

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-loaded with the trigger, followed by the four check criteria and codes, then the input shape, then the caveat. Dense and mostly waste-free, with minor redundancy in restating the schema's balcons field list verbatim.

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 read-only diagnostic with one nested parameter and no output schema, the description supplies the trigger, the exact rules and thresholds applied, and the reliability caveat. The only gap is that it never indicates what the response contains (presumably per-rule EB-* verdicts), which the agent must infer.

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% with a single nested object, so the baseline is 3. The description earns an extra point by attaching evaluation thresholds to specific fields (pente_pct >= 1 %, releve_etancheite_mm >= 150 mm), meaning the agent learns how each field will be judged, not just that it exists.

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 verb (VERIFIER) and a tightly scoped resource (balcony waterproofing: slope, upstand, drainage, guardrail) with the governing standard DTU 20.12. This is clearly distinguishable from the broader siblings cao_bim_etancheite and cao_bim_garde_corps by its balcony-specific scope, though no sibling is named explicitly.

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?

'Appelez quand vous devez VERIFIER L'ETANCHEITE DES BALCONS' gives an explicit activation trigger. It stops short of stating when NOT to use it or pointing to the general-purpose waterproofing/guardrail tools for non-balcony cases.

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