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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds a genuine behavioral prerequisite (mandatory decrire_outil introspection before use) but says nothing about error behavior for unknown operations, how 'arguments' are validated, or what the dispatch returns — and it names a non-existent operation, which undermines trust in the described flow.

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?

Reasonably short, but the instruction to call decrire_outil before use is stated three times in slightly different words ('avant usage' twice plus the final sentence), which is wasted space in an already under-specified description.

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?

This is a dispatcher over seven undocumented operations with an untyped nested arguments bag and no output schema. For that complexity, the description should enumerate what each operation does and what arguments each expects; instead it names only two operations and one of them does not exist, leaving the agent unable to select or populate a call without a second introspection round-trip.

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%: the seven-value 'operation' enum has no per-value documentation anywhere, and the nested 'arguments' object is completely unexplained (no indication of which keys each operation expects). The description compensates only minimally by naming two operations, one of which ('lire_source') is not in the enum, so it does not fill the coverage gap it needs to.

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 lists three loosely related domains (citation checking, authority hierarchy, act templates) but never states that this is a dispatch/facade tool routing to sub-operations, nor does it explain how those domains map to the seven enum values. It is distinguishable from siblings by topic area, but the agent must infer the tool's actual shape from the schema.

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 a concrete sequencing rule ('choisir une opération puis appeler decrire_outil avec son nom avant usage', and a chained flow for the two-operation case), which is real guidance. However, it offers no when-not-use or sibling comparison (e.g., versus explorer_jurisprudence or explorer_sources_francaises), and the recommended chain references 'lire_source', which is not among the enum operations.

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