BocaRoss

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful behavior beyond that: it lists what each result includes and explicitly says “Ne réserve rien” (does not book), clarifying that this is a search-only operation.

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 front-loaded with the purpose, followed by usage and result content, so it is easy to scan. However, the sentence listing returned fields duplicates information already available in the output schema, which slightly reduces conciseness.

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?

Given the annotations, the 80% schema coverage, and the presence of an output schema, the description is complete enough for an agent to call the tool correctly. It covers the search scope, location behavior, business types, and a clear no-booking constraint.

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 80%, so the schema already documents the parameters well enough. The description reinforces the optional location semantics (“près de moi” uses approximate position), but it does not add substantial meaning beyond what the schema and enum descriptions already provide.

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 gives a specific verb (“Trouve”) and a clear resource (“professionnels indépendants de l’automobile”), enumerating the relevant business types. It does not explicitly distinguish this search tool from the sibling detail tool fiche_pro, so it falls short of a 5 under the rubric.

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 explicitly tells the agent to use the tool whenever a user searches for a garage, body shop, inspection center, windshield service, or detailing near a city or near themselves. It provides clear context but does not state when not to use it or name the sibling alternative.

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 readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds content-level behavior beyond that: it discloses that prices appear only « quand ils sont publiés » and that vehicle-inspection centres expose DGCCRF-declared or network-displayed tariffs — useful caveats an agent would otherwise not anticipate. No mention of invalid-slug failure behavior.

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?

Purpose is front-loaded in the first clause, followed by the payload enumeration and a single usage sentence. The midsection is a long comma-list that could be trimmed, but every element adds selection value and there is no 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?

With an output schema present, the description needn't document return values, yet it summarizes them adequately for tool selection, and it names the input source and the use case. Only minor gaps remain (behavior on unknown slug, no explicit alternative when the professional is not yet identified).

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?

Single required param with 100% schema coverage, so baseline is 3. The description goes further by stating where the value comes from — « le champ « slug » rendu par chercher_pros, ou la fin de l’URL bocaross.fr/pro/… » — which tells the agent how to obtain and derive it, not just what format it takes.

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?

Specific verb+resource: reads the detail record of a BocaRoss professional from its slug. It enumerates the concrete payload (coordonnées, horaires sur sept jours, prestations avec prix, équipements, photos, prise de rendez-vous, tarifs DGCCRF pour un centre de contrôle technique), which clearly separates it from the sibling search tool chercher_pros.

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?

Explicit trigger given: « À utiliser quand l’utilisateur veut en savoir plus sur un professionnel précis ou le contacter. » It also routes the agent to chercher_pros as the source of the slug. There is no explicit when-not clause (e.g. what to do if the slug is unknown), so it stops short of a 5.

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