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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value by flagging that results are indicative and model-checked against 'cas de référence Marcel'. It also discloses the feasibility logic behind optionNetLePlusEleveFaisable (cash remaining after exit levy below price in nom propre, loan capped at cash in filiale), which is genuine behavioural detail an agent would not otherwise know.

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 domain and the tax scope, then inputs, then outputs — a logical ordering. The final clause is a very long nested parenthetical about feasibility conditions that is harder to parse than it needs to be, and some of that detail belongs in the output/schema documentation.

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?

With nine parameters, seven required and no output schema, the description does describe the principal returns (coûts, flux, net per option) and explains the two summary fields. It still leaves key inputs (tauxPret, tmiFrance, chargesAnnuelles) and the overall output shape/units under-specified, so an agent could call it but might not interpret values correctly.

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 11% (only region documented), so the description must compensate: it names trésorerie, prix, région, loyers and horizon, mapping to five of the nine parameters. However tauxPret, chargesAnnuelles, prixRevente and tmiFrance are never explained, and no units, currency or value ranges are given for any input.

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 (Compare) plus the exact resource and framing: two ways of holding a Belgian property from a French SASU, with the tax dimensions enumerated (revenu cadastral, droits d'enregistrement, plus-value, prélèvements sociaux). The country/SASU framing cleanly separates it from the other simulate_immo_* 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?

Usage is only implied by the country scope (Belgique) against siblings like simulate_immo_espagne or simulate_immo_uk; there is no explicit 'use this when / not when' or pointer to the alternative tool. It does list the expected inputs and outputs, which gives the agent enough to know what to supply, but not when to prefer this over another simulation.

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