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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description goes well beyond: it discloses the pricing model (5 credits per call), the methodology constraints (no VEFA, 1% €/m² trim), the null-return condition when INSEE suppresses small-population income, and the vintage_gap_years caveat about inflated ratios — all behavior an agent cannot infer from annotations.

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-loads the metric definition, then segments REQUIRED / NOT SUPPORTED / Returns / Cost with clear labels. Every sentence carries non-redundant information — no filler, and the most decision-relevant constraint (required locator) appears early.

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 compensates by enumerating the return fields (ratio_prix_revenu, prix_bien_median, revenu_median_annuel_uc, annee_reference, vintage_gap_years) and their edge-case null behavior. Combined with the input constraints and cost, an agent has everything needed 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?

Although schema coverage is 100%, the schema declares zero required parameters, while the description supplies the critical one-of constraint (at least one of code_postal/commune/code_commune) plus the uppercase format convention and the fact that code_commune bypasses commune resolution. It also explains which parameter combinations are unsupported, which the schema cannot express.

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 computation ('how many years of median income to buy the median property here') with both inputs named (median sale price over INSEE Filosofi median income). It explicitly distinguishes itself from analyze_market_statistics by noting the shared sales basis and from find_property_comparables as the right tool for other scopes.

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?

Gives an explicit REQUIRED clause (one of code_postal/commune/code_commune), an explicit NOT SUPPORTED clause (code_departement alone, latitude+longitude) with the reason, and names the alternative tools to use instead for those scopes. This is textbook when/when-not/alternatives guidance.

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