Recherche FFBB (multi-index)

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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), lowering the bar. The description adds one behavioral trait beyond annotations — results contain an 'id' consumable by ffbb_get or ffbb_club — but discloses nothing further such as result grouping, pagination behavior, or any auth/rate constraints. This matches the calibration case where annotation-covered safety with mild added context scores a 3.

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?

Five short lines, each a functional unit: the scope line, three type-mode bullets, and one follow-up sentence. The purpose is front-loaded before any parameter detail, and there is no filler or restatement of schema content.

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?

For a 5-parameter Meilisearch-backed tool with no output schema, the description covers the agent's core needs: what is searched, the best entry mode, how to narrow by type, and how to consume the result id. The only material gap is the undisclosed multi-index return shape — since no output schema exists, the agent cannot know whether results arrive flat or grouped by type — which keeps this just below a 5.

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. The description adds value beyond the schema by giving concrete semantics to the type enum — 'organismes' → clubs uniquement, 'competitions' → compétitions uniquement — and ranking 'all' as the best entry point, which the schema's one-line property descriptions do not convey. The query examples are redundant with the schema, but the type guidance is genuinely additive.

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 opens with a specific verb and resource — 'Recherche FFBB — clubs, compétitions, matchs, salles, tournois, etc.' — and immediately frames the scope as a multi-entity search. The closing note that results contain an 'id' to feed into ffbb_get or ffbb_club positions it as the entry-point search distinct from those retrieval siblings. An agent can tell this tool apart from the lookup-focused siblings without opening their schemas.

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 actionable guidance: 'type='all' → recherche globale (meilleur point d'entrée)' names the canonical entry mode, and the final sentence instructs the agent on the follow-up step. However, it never states when NOT to use this tool relative to search-adjacent siblings like ffbb_resolve_team or ffbb_team_summary, so the exclusions are left implicit.

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