Proposer une mémoire à revue

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

With no annotations provided, the description carries the burden of disclosure. It effectively communicates the pending state ('en attente'), the non-retrievability ('sans le rendre récupérable'), and the permanent outcome of human review ('l'approuver ou le rejeter durablement'). This adds valuable behavioral context beyond a simple 'add' description, though it omits details like side effects or reversibility.

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 two concise sentences, front-loaded with the core action and followed by the review consequence. Every word earns its place, with no redundant information, making it highly efficient.

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?

Given the tool's complexity (12 parameters, no annotations, no output schema), the description is too minimal. It does not explain parameter meanings, the review workflow's relation to siblings like memory_candidate_list/review, or any return/error behavior. The short description leaves significant gaps for an agent to invoke this tool correctly.

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 input schema has 12 parameters with zero description coverage, and the description provides no information about any parameter (subject, predicate, object, tags, evidence, etc.). The phrase 'un fait' hints at the triple structure but does not explain the semantics of optional fields, leaving the agent without guidance on parameter usage.

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 core function: 'Place un fait en attente sans le rendre récupérable' (places a fact on hold without making it retrievable). This distinguishes it from siblings like memory_add by specifying the pending state and non-retrievability, and it mentions human review, making the purpose unambiguous.

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 implies usage when a fact should not be immediately retrievable but rather await human approval, contrasting with direct add tools. However, it does not explicitly name alternatives or state when not to use this tool, so it provides clear context without explicit exclusions.

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