search_chunks

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

With no annotations provided, the description carries full burden. It explains the tool is read-only, details the default mean-centered scoring behavior, and mentions returning raw and centered scores. This goes beyond minimal disclosure, though it could include more on error handling or empty results.

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 two sentences with no unnecessary words. It front-loads the purpose and follows with crucial technical context. Every sentence adds value.

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 no output schema, the description hints at return values (raw and centered scores) and includes the prerequisite. It is fairly complete for a search tool, though could explicitly state the output format.

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 coverage is 100% with all parameters described. The description adds value by explaining the scoring mode behavior and the concept of anisotropic cosine bias, which provides deeper context beyond the schema descriptions.

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 'Search stored chunk embeddings by semantic similarity' with a specific verb and resource. This distinctly differentiates it from sibling tools like chunk_file, chunk_text, and embed which perform creation or embedding operations.

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 explicitly mentions the prerequisite of running index_all with with_embeddings=true first, and states it is read-only. While it doesn't explicitly list when not to use, the sibling tools cover alternative actions, providing adequate context for selection.

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