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

Annotations only declare readOnlyHint, and the description goes well beyond that: it discloses the login/auth precondition, the corpus limitation, the recency policy ('近期更正优先，旧话或过时'), the bounded result set, and the crucial negative-result caveat ('没命中不等于没说过'). That last point prevents an agent from concluding the user never said something, which is real behavioral value.

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?

Very compact and front-loaded — the primary trigger leads and every clause carries information about scope, recency, or limits. The telegraphic semicolon chain and the bare '登录;' opener cost some readability, so it is efficient but not maximally clear.

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?

For a 2-parameter read tool with no output schema and only a readOnlyHint annotation, the description covers auth, corpus scope, mode semantics, recency, and result bounds. It does not describe the shape of returned items or how many archive entries come back on an empty query, a minor residual gap.

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% and the schema already documents both the limit default of 8 and the empty-query archive behavior. The description's '(limit缺省8)' and archive wording restate the schema rather than adding new syntax or format semantics, so the baseline 3 applies.

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?

States a specific verb+resource (检索…本人原话) and immediately bounds the corpus: '只含自述，不含模型/他人内容'. That scope statement cleanly separates it from the many other search_* siblings (search_all, search_moments, search_people), which search other people's or general content.

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?

Gives an explicit trigger ('问用户前先查本人原话') and a mode-selection rule: empty query reads the direction/constraint/correction archive, non-empty query searches by topic. It does not name a competing sibling to route away from, so it falls short of full when/when-not coverage, but the usage context is unambiguous.

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