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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered and the bar is lower. The description adds the useful fact that this is an estimation ('Estime') covering a named set of payout components, but says nothing about underlying assumptions, default handling, or that the result is an estimate rather than an authoritative payroll calculation. Adequate with annotations, but thin on substance.

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?

A single sentence with the operation front-loaded and the output components enumerated in a compact list. Zero filler, nothing repeated from the schema or the title.

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 12-parameter, legally involved calculator with no output schema, the description does at least tell the agent what the returned figures will be. But it leaves open whether optional inputs (tauxCotisations, joursAcquisPeriode, decompteConges) are needed for a usable result, how components interact, and whether the tool returns a breakdown or a single total. Adequate but with clear gaps for the tool's complexity.

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 83%, so the schema carries most parameter meaning and baseline 3 applies. The description adds a loose mapping from components to inputs (préavis → preavisNonEffectueMois, 13e mois → moisPourTreizieme, prime de précarité → remunerationTotaleCDD, indemnité de rupture → indemniteRupture) which helps an agent understand which inputs unlock which outputs, but no format, dependency or default guidance.

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 uses a specific verb ('Estime') and a specific French payroll resource ('solde de tout compte'), then enumerates the six components computed (dernier salaire, congés non pris, préavis, 13e mois, prime de précarité, indemnité de rupture). An agent can tell exactly what it produces. It does not, however, name or distinguish itself from close siblings such as indemnite_licenciement, rupture_conventionnelle or conges_payes_indemnite, so it stops short of a 5.

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?

There is no explicit when-to-use guidance and no mention of alternatives, even though several siblings overlap heavily (indemnite_licenciement, rupture_conventionnelle, conges_payes_indemnite, preavis). The end-of-contract context is only implied by the term 'solde de tout compte' itself. The agent must infer routing from French labour-law domain knowledge.

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