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

'Lecture seule' merely repeats readOnlyHint=true, earning no credit. The genuinely additive content is the 'Indicatif — schéma signé et Consuel priment' disclaimer, which tells the agent the verdict is non-authoritative and must be superseded by signed drawings/Consuel — useful context beyond annotations. However, with no output schema, the description never says what is returned (findings list? per-circuit pass/fail? severity?), leaving a real behavioral gap.

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?

Trigger condition is front-loaded and every clause (rule codes, threshold mapping, disclaimer, read-only) carries information. It is a single dense run-on sentence chain with heavy parenthetical nesting, which costs some readability but no sentence is filler.

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 nested-object check tool with no output schema, the description explains the input shape and the rules applied, which is most of the burden. Missing: what the response contains, and the fact that 'scene' shows as not required (0 required parameters) is never addressed, so the agent cannot tell whether an empty call is valid or what it would check.

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 description coverage is 100% and the scene description in the schema reproduces the same field list ({nom, type, calibre_a, section_mm2, nb_points, protection_diff_ma}), so the description adds no syntax beyond the schema. The threshold table (1,5mm2->16A etc.) gives meaning to the expected values but is rule content rather than parameter contract, so baseline 3 applies.

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 and resource ('VERIFIER LES CIRCUITS ELECTRIQUES') and enumerates exactly what is checked: breaker/cable-section coherence, max 8 points, 30 mA RCD, minimum section by circuit type, each tagged with a rule code (EC-PROTECTION, EC-POINTS, EC-DIFFERENTIEL, EC-SECTION). It is clearly distinct from lighting/design siblings such as cao_bim_eclairage, though it never names an alternative tool 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 LES CIRCUITS ELECTRIQUES (NF C 15-100)' gives a clear triggering condition for the agent. It also bounds trust with 'Indicatif — schéma signé et Consuel priment', but gives no when-not-to-use case and no pointer to a sibling (e.g. cao_bim_conformite or cao_bim_eclairage).

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