Retrieval Diff

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

With no annotations, the description carries the full burden. It discloses the types of differences found (missing/shared chunks, score movement), but omits details on mutability, permissions, or side effects. The presence of an output schema partially offsets the need for return value transparency.

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 a single, front-loaded sentence that conveys the main purpose efficiently. However, it could benefit from structured bullet points for additional context.

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?

The description is incomplete: it lacks parameter semantics, usage guidance, and behavioral context. The output schema exists, but the description does not hint at the output structure or how the results relate to the inputs.

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%, and the description fails to explain any of the three parameters. It does not clarify what run_id_a/b represent or the meaning of the match_by enum, leaving the agent to infer from names.

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 that the tool compares two retrieval runs to find missing chunks, shared chunks, and score movement. It effectively communicates the core function, but does not explicitly distinguish it from sibling tools like retrieval_observe or retrieval_stats.

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 guidance is provided on when to use this tool versus alternatives, nor are there any exclusions or prerequisites mentioned. The description simply states the action without contextual usage advice.

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