kb_search

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

With only readOnlyHint: true in annotations, the description adds value by explaining that queries should be in the same language as documents, that results are top matching chunks with source and score, and that scoping/filtering is optional. It provides more behavioral detail than a simple read-only flag, without any contradiction.

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 three sentences, front-loaded with the core purpose, and every sentence earns its place. There is no redundant information or filler, making it highly concise and well-structured.

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 search tool with no output schema, the description covers the return value (top chunks, source, score) and the query format, which is adequate for core use. The unexplained 'config' parameter and lack of mention of required fields (though schema handles that) are minor gaps, but overall the description is sufficiently complete for an AI agent.

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 bears the responsibility of explaining parameters. It successfully maps most params: project_id ('a project's KB'), query ('natural language'), collection_id ('scope to one KB'), metadata_filter ('filter by metadata'), and max_results ('top matching chunks'). However, the 'config' param remains completely unexplained, a notable gap.

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's function as 'Semantic search across a project's KB' with a specific verb and resource. It further distinguishes from sibling KB tools like kb_list or kb_get_document by describing the output ('top matching chunks with their source + score') and the natural language query requirement.

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 implies usage for semantic search on a project's KB, highlighting natural language input and optional scoping or filtering. It does not explicitly exclude alternatives or name when not to use it, but the context is clear enough for an agent to select this tool over listing or document retrieval tools.

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