Search the project's formal knowledge base to find relevant facts, patterns, and solutions, returning a limited preview within a set character budget. Use it to locate entries before reading full content.
检索本项目正式知识的有限预览；完整正文使用knowledge_read。预算是JSON正文字符数，默认6000。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| filters | No | ||
| max_chars | No | ||
| context_handle | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses that results are a 'limited preview' and that the budget is measured in JSON body characters with a default of 6000, but it does not explain result ranking, truncation behavior beyond 'preview', or any access constraints.
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 tight sentences with the purpose, sibling routing, and budget default front-loaded. The only slight issue is that '预算是JSON正文字符数' does not name the max_chars parameter, making the budget reference mildly ambiguous.
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 five parameters including a nested filters object, no annotations, and no output schema, the description is too thin. It covers purpose and one budget detail but gives no guidance on filters, limit, or context_handle, which an agent would need to use the tool beyond a bare query.
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 only explains one parameter's semantics (the budget/max_chars unit and default of 6000) and leaves query, limit, the nested filters object with seven subfields, and context_handle completely undefined.
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 states a specific verb (检索/search) and resource (本项目正式知识/project formal knowledge), and explicitly distinguishes the tool from its sibling knowledge_read by saying this is only a limited preview while full text requires knowledge_read. An agent can immediately tell what the tool does and how it differs from the adjacent read 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?
It explicitly routes the agent: use this tool for a limited preview, and use knowledge_read when the full text is needed. That names the relevant alternative and the condition that selects it, leaving little to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.