wiki_search

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

With no annotations at all, the description carries the full behavioral burden and does add real context beyond the schema: the source is unofficial/student-built (a reliability caveat) and deep=true triggers a first-time full-site crawl costing a few seconds (a latency/caching warning). It still omits return shape and whether results are ranked, so it is strong but not complete.

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?

One compact sentence with the resource and the important deep-mode caveat front-loaded in a parenthetical. Nothing is wasted, though the parenthetical stacking makes it slightly dense.

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 simple three-parameter read tool with a fully documented schema and no output schema, the definition covers what is needed to call it, but it leaves the relationship to wiki_page/site_search unresolved and gives no hint about result fields or ranking.

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 all three parameters are already documented in the schema. The description reinforces deep=true with extra meaning (it pulls full article text and incurs a crawl cost), but says nothing about limit or the semantics of query beyond what the schema states, so this sits at the baseline.

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 a specific verb (检索) and a specific resource (WikiLake 校园百科), plus a provenance qualifier (学生自建，非官方) that tells the agent this is a student-run wiki rather than an official source. It is clearly distinguishable from wiki_page by being a search rather than a page fetch, though it never names that sibling explicitly.

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?

Usage is only implied: the mention of deep=true '连正文一起搜' hints at when to enable the expensive mode, but there is no explicit statement of when to use wiki_search versus wiki_page or site_search, and no prerequisites or exclusions are given.

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