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

Annotations already declare readOnlyHint/true, idempotentHint/true, destructiveHint/false and openWorldHint/true, so the safety profile is covered. The description adds one genuinely behavioral detail beyond that: a mandatory prerequisite step (call decrire_outil with the chosen operation name to obtain its contract before use). It says nothing about the fact that results are federated across heterogeneous external sources, about latency, or about rate limits.

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 purpose is front-loaded, but the last two sentences say the same thing twice: "appeler decrire_outil avec son nom avant usage" and "Appeler decrire_outil avec nom = opération choisie pour obtenir son contrat exact avant usage." That redundancy costs a third of the description's length for zero added information.

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, but the tool delegates per-operation contracts to decrire_outil, which is a legitimate completeness strategy for a dispatcher. What remains missing is disambiguation against explorer_doctrine_archivee and any hint about the shape of the 'arguments' payload.

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%, so the description must carry the burden. The ten enum values are self-describing for 'operation', and the instruction to resolve the contract via decrire_outil is a real mitigation, but the 'arguments' envelope — a free-form nested object with additionalProperties:true — is left entirely unexplained (what keys, keyed by operation, optional vs required).

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 the resource domain ("Doctrine et thèses ouvertes") and hints at intent ("identifier le fonds, l'auteur et la publication"), but gives no verb — it is a noun phrase, not a statement of what the tool does. It also fails to distinguish itself from the sibling explorer_doctrine_archivee, leaving the agent to guess what "ouverte" excludes.

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?

"Choisir une opération puis appeler decrire_outil" is invocation mechanics, not usage guidance — it says how to call, not when to call this instead of explorer_doctrine_archivee or explorer_fonds_et_couverture. No conditions, no exclusions, and nothing about which of the ten operations suits which research question (theses juridiques vs HAL vs DOAJ vs Persée).

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