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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that with the disclaimer 'Indicatif, pas une note de calcul signee', telling the agent the output is an estimate of limited engineering authority — a behavioral trait not present in structured fields.

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?

It is a single dense sentence with the use condition front-loaded, which is good. However, the long inline enumeration of calculation variants largely duplicates the `type` schema description and makes the sentence run-on, costing readability without adding new information.

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 26-parameter calculator with no output schema and near-zero schema description coverage, the agent needs param-to-mode mapping and expected return shape. The description supplies neither — it names the modes but not their required inputs or outputs, so a correct invocation is not derivable from the definition alone.

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 only 4% across 26 parameters. The description does enumerate the 13 allowed values of the discriminating `type` parameter, which is genuinely useful dispatch information. But it says nothing about which of the 25 numeric inputs (g_kn, lx_m, as_m2, cu_kpa, perimetre_controle_m, etc.) apply to which calculation type, so the agent cannot map inputs to modes from the description.

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 states a specific verb and resource ('obtenir un ordre de grandeur de calcul structure (EC2 simplifie)') and enumerates the calculation families covered (poutre, dalle, poteau, poinconnement, voile, pieu, combinaisons...), so an agent can tell it apart from siblings like cao_bim_descente_charges or cao_ferraillage. It is clear but doesn't explicitly differentiate itself from those adjacent siblings.

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 opening 'Appelez quand vous devez obtenir un ordre de grandeur de calcul structure' gives a use condition, and 'Indicatif, pas une note de calcul signee' implies a scope boundary. However, no alternative tool is named and no exclusion (e.g., vs. descente_charges or ferraillage) is stated, leaving routing to be inferred.

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