memories

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

There are no annotations to lean on, but the description does disclose meaningful behavior: results are facts (people, preferences, agreements, numbers) that carry sources ('带出处'), and the default empty-query behavior is stated. It does not state that the tool is read-only or clarify what happens to the results (ordering, truncation).

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 short, front-loaded clauses with zero waste; the resource definition comes first and the mode-specific behavior second.

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?

The tool has an output schema, so return shape need not be described, and the description still tells the agent what kinds of objects come back and that they carry sources. The only real gap is the unexplained `limit` and the lack of sibling routing guidance.

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 compensate. It fully explains `query` semantics ('empty returns most recent'), but `limit` is not mentioned in the description at all (only its default 50 in the schema). Half-documented parameters warrant a middling score.

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 definition names a specific resource – long-term facts extracted from events, with provenance – which is distinct from sibling tools like `search` (raw search) and `insights` (aggregated patterns). The retrieval verb is only implicit (it doesn't say 'return/list'), but 'query 留空返回最近的' makes it clear this is a retrieval tool.

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 explains one mode explicitly: empty query → return most recent. However, it never routes the agent to or away from alternatives such as `search`, `insights` or `list_records`, so selecting this tool over a sibling is left to inference.

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