panorama_implantation_complet

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

Annotations already indicate read-only (readOnlyHint=true), non-destructive, idempotent, and open-world. The description adds substantial behavioral context: it describes degradation flags ('couverture' with ok/partiel/indisponible), total rejection on geocoding failure (RangeError), internalized pitfalls (PLM mode for big cities, precise count for prescriptors, centroids for CDS). No contradictions with annotations.

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 well-structured with sections: purpose, sections list, output format, degradation, pitfalls, workflow. It is front-loaded with the main purpose and clearly separates each aspect. Every sentence adds value given the tool's complexity (7 parallel sections, multiple fallbacks). No fluff.

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 complex (7 sections, many data sources, failure modes, no output schema). The description covers all essential aspects: what each section returns (summaries, not raw lists), degradation flags, fallback to sibling tools, workflow, and internalized pitfalls. It also explains the output format (count/top-N/average) and that no business interpretation is performed. Given the absence of an output schema, the description fully compensates.

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?

Input schema covers 100% of parameters with descriptions. The description adds context: adresse is internally geocoded via IGN, point skips geocoding and requires code_insee, rayon_km defaults to 5. It clarifies the XOR relationship between adresse and point. While schema handles basic meaning, the description enriches with workflow context and constraints.

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 clearly states the tool's purpose: 'Étude d'implantation labo en 1 appel' (lab site study in one call). It specifies it geocodes and aggregates 7 sections in parallel, replacing ~15 individual MCP calls. This distinguishes it from siblings like the unit tools (e.g., etablissements_finess_in_radius). The verb 'panorama' and noun 'implantation' precisely convey the tool's role.

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 provides explicit workflow: call this tool to start a study, then drill into partial/unavailable sections using unit tools, then enrich concurrents. It states when to use (first step) and when not (not to interpret business meaning). It also details fallback actions for degraded sources, listing specific sibling tools to use. This is comprehensive guidance.

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