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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the agent knows it's safe. The description adds value by disclosing the return cap ('jusqu'à 10 candidates triées par score') and the precision scaling with DPE criteria. This goes beyond what annotations alone provide, covering key behavioral aspects like output limit and result ordering.

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 description is three sentences, each adding value: the main purpose, the equivalence to geolocate_listing, and the precision/return behavior. It is front-loaded with the core action. While compact, it is slightly dense but does not waste words. The structured flow makes it easy to parse.

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 11 optional parameters and no output schema, the description gives essential context: returns up to 10 candidates sorted by score. It also hints at the source data (DPE/DVF). However, it does not describe the structure of each candidate parcel (e.g., identifiers, fields), nor error conditions. Given the complexity, this is a notable gap; an agent might not know what to do with the 'candidates' output without further detail.

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 low (45%), so the description must compensate. It lists categories of criteria (commune, surface, classe et consommation DPE, GES, date, année de construction, terrain) but does not map them to exact parameter names or formats. It does mention that more DPE criteria (consumption, GES, date) improve precision, giving some semantic context. However, it leaves many parameters (e.g., type_bien, classe_ges, anne_construction) unexplained, so the compensation is partial.

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 clearly states the verb 'Identifie' and the resource 'parcelles candidates d'un bien immobilier'. It explains the input is property characteristics from an ad, and it cross-references DPE and DVF data. It differentiates from siblings like geolocate_listing by noting it's equivalent without URL or quota, and implies a distinction from address-based search tools.

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?

The description provides usage context: when you have property characteristics (commune, surface, DPE, etc.) and want to find candidate parcels. It explicitly notes it's an alternative to geolocate_listing without URL/quota. However, it does not contrast with find_parcelles_by_address or search_parcelles, so the when-not-to-use guidance is incomplete. Still, the intended scenario is clear.

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