search_docs

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool does not establish a Houdini TCP connection, loads a local RAG index, returns a specific envelope, and handles error cases (rag_index_missing, rag_index_unavailable, _index_warning). This is high-value transparency beyond simple read/write hints.

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?

The description is well-structured with clear sections (main purpose, connection detail, usage contrast, parameter details, return envelope) and front-loads the core functionality. It is somewhat verbose, including implementation details like 'apply_response_cap' and tokenizer internals, but these earn their place given the lack of annotations and output schema.

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 the tool's moderate complexity, no annotations, and no output schema, the description covers the return envelope, error states, and parameter behavior adequately. The missing ctx parameter and lack of environment prerequisites (e.g., prebuilt index location) are notable gaps, but the overall details are sufficient for an agent to use the tool effectively.

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?

The description richly explains the query parameter (tokenizer preserves hou.xxx() and /obj/geo1 semantics, underscore compound handling) and limit (clamp to [1,50], default 10), adding meaning absent from the schema. However, it completely omits the required ctx parameter, leaving its purpose unclear. This gap prevents a higher 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 description clearly states the tool performs BM25 retrieval across Houdini documentation ('跨 Houdini 文档做 BM25 检索'), specifying the bridge-local mode and explicitly contrasting with get_houdini_help/verify_hou_api. This distinguishes it from sibling tools and identifies the specific resource and operation.

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 provides explicit guidance on when to use this tool: for cross-document thematic searches ('跨文档主题检索') such as examples given, and when NOT to use it (single API/node structured queries better served by get_houdini_help/verify_hou_api). This clearly delineates usage against alternatives.

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