Recherche dans les règlements sportifs FFBB

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

Beyond the annotations, the description discloses concrete behavior: it is deterministic, uses SWR caching, returns a dict with extraits[] containing document_id, article_number, score, and extrait, and sorts results by relevance. This adds useful context beyond the readOnlyHint/idempotentHint annotations without contradicting them.

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 structured into three focused paragraphs: the core function and scope, the return value and behavioral properties, then usage guidance with alternatives. Every sentence delivers useful information, and the key purpose and exclusions appear early.

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 search tool with 7 optional parameters, no required fields, and no output schema, the description is complete: it covers what the tool searches, what it returns, how results are ordered, its side-effect-free behavior, when to use it, when not to use it, and which parameters to refine with. The rich schema fills the remaining 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?

The schema already documents all 7 parameters with examples and defaults, so the description does not need to repeat them. The line 'Affûte avec level, organizer, category et limit pour réduire le bruit' adds a small amount of grouping/purpose information, but it is not essential given the 100% schema coverage.

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 names a precise verb and resource: 'recherche plein texte déterministe dans les règlements officiels FFBB, régionaux et départementaux.' It further clarifies the scope by listing concrete topics such as qualifications, montées/descentes, and forfaits, and it distinguishes itself from the relevant sibling tools (ffbb_get_regulation_article, ffbb_list_regulations, ffbb_explain_tiebreak_rules).

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 is explicit about when to use the tool: 'quand tu ne connais pas le numéro d'article et que tu cherches par mots-clés.' It also gives explicit exclusions and alternatives: use ffbb_get_regulation_article for a specific article, ffbb_list_regulations to list documents, and ffbb_explain_tiebreak_rules for tiebreak explanations, so an agent is not left guessing.

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