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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real context on top: the France-Greece convention is applied, the result is capped by reference 'cas Marcel' and explicitly labelled 'résultat indicatif' rather than a recommendation. It also spells out the two feasibility conditions (cash remaining after exit levy below price in nom propre; loan capped at cash in filiale with the funding gap not modelled) — a genuine behavioural caveat about model limits. It stops short of stating units/currency or rounding for the outputs.

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?

The purpose and inputs are front-loaded, which is good, but the closing parenthetical explaining optionNetLePlusEleveFaisable is a single dense run-on nesting two separate feasibility rules. It carries necessary information yet is hard to parse in one pass and would be much clearer as a short bulleted list.

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 no output schema, the description correctly takes on the return contract, naming coûts, flux, net per option plus the two summary fields and their semantics. For an 8-parameter simulation with only 25% schema coverage, the main residual gap is that most required parameters are never given units or expected ranges, but the decision-relevant behaviour is covered.

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 only 25%, so the burden falls on the description, and it partly discharges it by naming trésorerie, prix, loyers and horizon as the inputs. However, chargesAnnuelles, prixRevente and horizonAnnees get no unit, currency or interpretation help, and the mapping from the prose labels to the camelCase parameter names is left for the agent to bridge.

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 opens with a specific verb+object ('Compare deux façons d'investir en Grèce depuis une SASU française') and enumerates the exact tax mechanics being compared (barème locatif progressif, suspension des plus-values, filiale, prélèvements sociaux). The Greek jurisdiction in the name plus the explicit French-SASU framing cleanly separates it from the simulate_immo_belgique/espagne/italie/portugal 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 implied by the geography and by 'Compare deux façons' — an agent can infer this is the Greek two-structure comparison. But there is no explicit when-to-use/when-not statement, no mention of when a sibling like simulate_immo_portugal or compare_allocation would be the better pick, and no stated preconditions for the inputs.

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