feedback.preservation

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

Description explicitly says read-only and no revert, which addresses behavioral aspects. No additional details about consequences of missing baseline, performance, or error states. Lacking annotations, description carries the burden and partially meets it.

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?

Single, efficient sentence that conveys core purpose and key behavioral trait (read-only). No wasted words. Front-loaded with key information.

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?

Describes what metric is computed but not output format or how results are returned. Lack of output schema means description should clarify return value, which it doesn't. For a metric tool, explanation of interpretation is missing.

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 single optional parameter 'object' is described only by its schema title; the description adds no extra meaning beyond what the schema already provides. With 0% schema description coverage, the description should compensate but does not.

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?

Description clearly states it's a 'do-no-harm metric' computing silhouette IoU and bbox delta against a stored baseline, with read-only constraint. Distinguishes from other feedback tools. However, jargon like 'silhouette IoU' assumes domain knowledge.

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 explicit guidance on when to use this tool vs alternatives like feedback.quality or feedback.silhouette. 'Do-no-harm' hints at safety checking, but no when-not or alternative tools are mentioned.

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