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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: the null return when INSEE suppresses a commune's income figure, the 5-credit cost, and the exact data sources. It does not cover auth or pagination, but for a read-only analytics call this is substantially richer than the annotations alone.

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 definition is front-loaded with the metric in the first sentence, then blocks for required inputs, unsupported scopes, return values, and cost. Each section is short and earns its place; no filler or repetition of 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?

With no output schema, the description correctly enumerates the returned fields (ratio_prix_revenu, prix_bien_median, revenu_median_annuel_uc, annee_reference) and explains the null case. Together with the locator constraints and cost disclosure, an agent has everything needed to call and interpret this tool.

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 100%, so the baseline is 3, but the description adds a cross-parameter constraint the schema does not encode — 'You MUST provide one of' three locators — despite zero parameters being marked required. It also clarifies that code_commune bypasses commune resolution and rejects lat/lon and departement scopes, which the schema does not 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?

The description states a specific metric — 'how many years of median income to buy the median property here' — and names the exact data sources (DVF price/surface medians crossed with INSEE Filosofi median income). It also distinguishes itself from analyze_market_statistics and find_property_comparables by naming them as the right tools for the unsupported 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?

It gives explicit when-to-use conditions (one of code_postal, commune, code_commune), explicit when-not conditions (code_departement alone, latitude+longitude), and justifies the exclusions with reasoning about commune boundaries and income aggregation. Alternatives are named for the excluded scopes, leaving nothing to inference.

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