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

Annotations already declare readOnly/destructive/openWorld; the description reinforces with 'Lecture seule' and adds valuable caveats — the result is 'Indicatif' and a signed EC5 note is obligatory. It also discloses the computation method and thresholds, which annotations can't. Lacks detail on output shape, but no output schema exists.

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 and dense with relevant technical details, but it's a single long run-on construction that packs formula, thresholds, schema, and disclaimer together with little structure. Every element earns its place, but readability suffers.

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 one-param nested-scene tool with no output schema, it provides enough — formula, thresholds, enum values, and the indicative/signed-note caveat — for an agent to call it and interpret results. Minor gap on return-format expectations.

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 baseline is 3; the description goes further by spelling out the nested planchers_vibration fields, the i_m4_par_m vs section {b_mm,h_mm}+entraxe_mm alternative, and the usage enum values (habitation|bureau|public). This meaningfully exceeds the schema's one-line summary.

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?

Names a specific verb and resource: verify the vibration comfort (EC5 natural frequency) of a floor. It's clearly differentiated from neighbor tools like cao_bim_acoustique or cao_bim_structure by naming the exact check (f1 estimated via 18/√δ, ≥8 Hz in residential).

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?

Opens with an explicit trigger: 'Appelez quand vous devez verifier le CONFORT VIBRATOIRE d'un plancher'. It gives clear context for when to call it, but doesn't name alternatives or exclusions among the many structural siblings.

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