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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Lecture seule' is a restatement rather than added value. The genuinely additive element is 'Indicatif — note de calcul de longrine signee prime', which warns the agent the output is non-authoritative. Nothing is said about what the verification returns or how non-conformities are surfaced.

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 call trigger and packed into two dense sentences with no filler. Slight redundancy in restating the 'scene' object shape already given by the schema, but overall the information density is high.

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 single optional-parameter, read-only check with no output schema, the description covers purpose, scope, the four verification axes, and the authoritative-source caveat. It does not say what a verdict looks like or what happens if 'scene' is omitted (the parameter is not required), which is a residual gap.

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% and the single nested 'scene' property is already documented, so the description's 'scene : longrines {section, armatures, liaison, niveau}' largely duplicates the schema. The LG-* codes hint at the expected content of each nested field, which is a marginal addition. Baseline 3 is appropriate since the schema carries the load.

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 ('VERIFIER LES LONGRINES') and disambiguates the resource with a gloss ('poutres de liaison au sol'), then enumerates the four checked aspects with mnemonic codes (LG-SECTION, LG-ARMATURES, LG-LIAISON, LG-NIVEAU). An agent can distinguish this from neighbours like cao_bim_semelles or cao_bim_poutres_lamelle_colle by the explicit mention of footing/column tie. It stops short of naming an exclusion or the sibling it replaces.

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...' gives a clear trigger condition, and the closing 'Indicatif — note de calcul ... signee prime' tells the agent when this result should not be treated as authoritative. No negative guidance (when NOT to use it) and no named alternative tool, 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.