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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds citation requirements and behavior (returns smaller windows with interview_id), which is useful. However, it doesn't disclose performance limits or edge cases, so a middle score is appropriate.

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 concise, front-loaded with the purpose and scoping behavior, and includes crucial citation instructions without excessive detail. Each sentence contributes to effective use, from purpose to expansion options.

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 explicitly lists the return fields (matching_chunks with chunk_index, text, similarity, start_seconds?, url), which is sufficient for an agent to process results. It also covers citation format and expansion, making it complete for a read-only search tool. Slight deduction for not detailing how to handle empty results or errors.

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?

Although schema coverage is 100%, the description adds meaning beyond the schema by explaining how interview_id affects the result window size, and by specifying context for the query as a hypothesis/claim. The limit and chunks_limit defaults are in the schema, but the description clarifies their behavior in relation to interview_id, adding value.

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 it is a semantic search for evidence/counter-evidence, specifying the resource (interview context) and the distinguishing feature of optional scoping by interview_id. It differentiates from siblings like interviews_read by focusing on hypothesis-driven evidence retrieval rather than reading interviews.

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 guides when to use the tool (after obtaining interview context) and how to expand results (via interviews_read action=transcript), providing clear alternatives and next steps. It does not state when not to use it, but the context condition is sufficient.

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