Ajouter une mémoire

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

With no annotations, the description carries the full burden. It discloses that the tool writes and that rejected values are blocked at write time, which is valuable context beyond the schema. However, it omits details about the 'reinforce' behavior (e.g., what happens on duplicate facts), idempotency, or error handling.

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?

Two sentences deliver the core action and a critical constraint without excess. The description is front-loaded with the primary verb and resource, then provides the rejection caveat. Every word earns its place.

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?

Despite a rich schema, the description lacks connection to the surrounding workflow (memory_candidate_add, memory_verify, etc.). The rejection behavior hints at a review process but does not explain when to use this tool versus alternatives. With no output schema, more contextual guidance was needed.

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 100%, so the baseline is 3. The description groups optional confidence, evidence, and validity period but does not add new meaning beyond the schema's parameter descriptions. No compensation needed.

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 uses 'writes or reinforces' as a specific verb and identifies the atomic fact (subject→predicate→object) as the resource. It also mentions the rejection-by-human-review behavior, which subtly distinguishes it from candidate/review workflows and aligns with the tool's purpose.

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?

No explicit when-to-use or when-not-to-use guidance is provided. The description implies it is for persisting a fact but never mentions alternatives like memory_candidate_add (for review) or memory_add_many (for batch), leaving the agent to infer context from sibling tool names.

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