Search locally stored project conventions, prohibitions, and repair lessons by query and role to recall approved rules before coding tasks.
Search the knowledge base (FTS5 + CJK bigram by default; embedding is optional). 搜索知识库（默认纯 FTS5 + CJK bigram；embedding 为可选增强）。
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | 角色过滤 | |
| query | Yes | 检索查询 | |
| top_k | No | 返回条数上限 |
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 burden. It does disclose something genuinely useful about matching behavior (default pure FTS5 + CJK bigram, embedding as optional enhancement), but says nothing about read-only safety, ordering/ranking, result size behavior, or permissions — gaps that matter for a search tool with no output schema.
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?
Front-loaded with the core action, but the entire sentence is duplicated in Chinese with no added information, roughly doubling length for a one-line tool. No wasted hedging beyond that, but the parallel-language repetition is pure redundancy for a token-sensitive agent.
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?
A read-only, 3-parameter search with fully documented parameters and no output schema needs modest description — and this covers the mechanism but not what comes back (count, ranking, snippet format) or how to choose between the default FTS mode and the optional embedding path. Adequate but with clear gaps given a crowded sibling set.
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 query, role and top_k are already documented in structured form; baseline 3 applies. The description adds no syntax hints (e.g., quoting, CJK tokenization implications of the bigram mode) or guidance on how role/top_k interact with the search mode.
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 and resource ('Search the knowledge base') and adds the retrieval mechanism (FTS5 + CJK bigram, optional embedding), which clearly separates it from the write-side siblings rsi_knowledge_add/update/delete. It does not differentiate itself from read-side siblings such as rsi_recall or rsi_explore, so an agent still cannot tell which retrieval tool to pick.
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 when-to-use or when-not-to-use guidance, no mention of prerequisites, and no routing among the many sibling retrieval tools. The only usage-like signal is the incidental note that embedding is optional, which concerns internals rather than selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.