Recherche FFBB (multi-index)

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety/freshness profile is largely covered. The description adds one real behavioral nuance — that free-text street names cause homonymy problems for halls, so commune/code_postal should be preferred — but says nothing about result volume, data freshness (despite force_refresh existing), or pagination behavior. Some added value, not rich context.

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?

A one-line scope statement followed by four tight routing bullets: front-loaded, scannable, and every line carries actionable information. No filler, no repetition of schema field definitions.

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 read-only, 10-parameter multi-index search with no output schema, the description covers scope and correct tool selection well. It would be slightly stronger if it noted what the result set looks like (mixed entity types? per-index grouping?) and the effect of compact/force_refresh, since there is no output schema to fall back on.

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 100%, so the baseline is 3. The description earns a bump by giving semantic guidance for two parameters — commune and code_postal — explaining *why* to use them ('évite homonymies rues') rather than merely restating them. It does not, however, add anything for sort, filter_by, compact, or limit, which remain schema-only.

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?

Opens with a specific verb+resource ('Recherche FFBB unifiée') and enumerates the entity types it spans (clubs, compétitions, matchs, salles, tournois), which usefully complements the `type` enum that uses different labels (organismes, rencontres). The routing bullets make it immediately distinguishable from specialist siblings like ffbb_next_match and ffbb_match_lookup.

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 'Recommandations LLM' block explicitly names alternatives and the conditions that select them: next match → ffbb_next_match/ffbb_team_summary, direct confrontation → ffbb_match_lookup/ffbb_head_to_head, club calendar → ffbb_club, halls by city/postcode → code_postal/commune. This is a rare case of genuine when-to-use-else guidance rather than vague context.

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