Estimatiz

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

Annotations declare readOnlyHint=false and idempotentHint=false, and the description adds real value: it discloses that a non-indexable report is persisted, that anyone with the link can access it, and that no personal data (name, email, phone) is collected. It does not explain whether repeated calls create duplicate reports or how the link is secured, but the disclosure exceeds what the annotations carry.

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?

Four sentences, front-loaded with the core computation before the persistence side effect and absence of PII. No padding, though the final sentence about not requiring name/email/phone is somewhat tangential to invoking the tool.

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?

An output schema exists, so the description's recap of low/median/high amounts is bonus rather than necessity, and the report-persistence behavior is well covered. However, with 6 parameters, a nested address object, and 17% schema coverage, the three room/location parameters are left undocumented in both schema and description.

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 only 17%, so the description must carry parameter meaning. It names address, property_type and surface at a high level but supplies no semantics for rooms, rooms_mode, or location_fallback, and adds no format, range, or enum detail beyond what the schema already states.

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 ('Calcule une estimation immobilière Estimatiz') plus its two side effects (persisting a report, returning amounts). 'à partir d'une adresse sélectionnée' implicitly distinguishes it from the sibling search_addresses, which produces the address this tool consumes.

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 phrase 'adresse sélectionnée' implies the address must first come from search_addresses, but neither that tool nor the condition for choosing it is named explicitly. There is no when-not guidance or prerequisite statement beyond the implied address selection.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context beyond that: the response can contain multiple addresses and the user selects their property from them. It does not cover pagination or matching semantics, but the safety profile is already annotated.

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?

Two short sentences, front-loaded with the core search action and then the result-selection behavior. Every sentence contributes and there is no redundant filler.

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?

The tool is a simple one-parameter read-only search with annotations and an output schema, so the description need not explain return values or safety. It covers purpose and result multiplicity, but omits explicit usage relative to estimate_property and query format details.

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 carries the burden for the single parameter q. It only identifies q as a query ("correspondant à une requête") without format, examples, or matching rules. For one simple parameter, this is minimum viable but leaves clear gaps.

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 ("Recherche") and resource ("adresses connues d’Estimatiz") and adds that results are matched to a query. It does not explicitly name or distinguish itself from the sibling estimate_property, so it stops short of a 5.

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 implies a query-driven address lookup but gives no explicit when-to-use guidance and does not mention the sibling tool or any alternative. It offers no when-not conditions or routing help.

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