Construire un rapport d’enquête consolidé

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

With no annotations the description carries the full burden, and it does disclose meaningful behavior: it mandates a documentary evidence path per ramification, allows links from acts to be injected as documentary paths, and states that family, ownership, usufruct, representation and transactions are never inferred from a name or address. It omits cost/latency, auth needs and whether the call mutates state, which keeps it short of 5.

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?

Three sentences, front-loaded with the orchestration role and a single dense enumeration of outputs, followed by the input-constraint note. The output list is long but each item earns its place; no filler or repetition against the title.

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?

There is no output schema, and the description usefully enumerates what the report returns, which compensates for that gap. However, for a 7-parameter tool with nested objects and zero schema descriptions, the semantics of most inputs and the cost/aggregation implications of orchestrating many official sources remain unexplained.

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 0% across 7 parameters, several deeply nested, so the description must compensate. It adds real meaning for documentary_relationship_paths (injectable links drawn from acts) and touches financing via 'disponibilité financière', but says nothing about siren, max_people, max_companies_per_person or the documentary_findings/external_observations structures.

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+resource ('Orchestre les sources officielles' producing a consolidated investigation report) and enumerates the returned sections (identity, relationship map, material findings, SCI, financing, procedures, sanctions, contradictions, quality gates). This clearly separates it from single-source siblings like get_company_snapshot or analyze_economic_footprint, although no sibling is named explicitly.

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 states the tool works around 'un sujet pivot' and requires an evidence path per branch, which implies heavy multi-source investigation, but it never says when to prefer this over cheaper siblings (snapshot, mandate graph) or what prerequisites must be gathered first. Usage is implied rather than stated.

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