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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: it explains the returned fields (costs, flows, net per option), the meaning of optionNetLePlusEleve, the exact conditions under which optionNetLePlusEleveFaisable is false, and warns that results are indicative and not a recommendation.

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 scope, then inputs, then outputs and feasibility caveats, in a logical order with no filler sentences. The faisabilité parenthetical is long but carries substantive information rather than padding.

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 fairly complex two-scenario comparison with 8 inputs and no output schema, the description does well on scope and return-value semantics. It still leaves four parameters unexplained and gives no indication of units or magnitude conventions, which an agent needs to call it 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 0%, so the description must carry parameter meaning, but it only summarizes four inputs in a single clause ('trésorerie, prix, loyers, horizon') and omits chargesAnnuelles, prixRevente, tmiFrance and tauxPret entirely. No units, currency, or rate conventions (e.g. whether tmiFrance is a fraction or percent) are given, leaving half the inputs undocumented anywhere.

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: comparing direct ownership vs. a local company for a Saint-Barthélemy property held from a French SASU, for a French tax resident. This clearly separates it from the other simulate_immo_* siblings, which target different jurisdictions.

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?

Establishes the exact applicability conditions (French SASU, French tax resident, Saint-Barthélemy property) and explicitly excludes Saint-Barthélemy tax residency from the calculation. It never names an alternative sibling or states when to prefer another tool, which keeps it short of a 5.

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