feedback-preservation

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

With no annotations provided, the description carries the full burden. It transparently says 'read-only, no revert' and explains the computation method (mean/min silhouette IoU plus bbox delta). This goes beyond a simple claim, but it omits details like output format or what happens if no baseline exists, though the schema hints at defaults.

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 sentence that front-loads the key action ('Do-no-harm metric') and immediately provides the computation details. It is efficient and to the point, though it packs a lot of technical terms, which may reduce readability. No unnecessary words.

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 the tool is a read-only metric with one optional parameter and no output schema, the description explains what it computes but does not specify the return value or how the metric is reported (e.g., returning a number, a message). It also assumes familiarity with terms like 'silhouette IoU' and 'bbox delta' without elaboration. It is adequate but leaves gaps for an agent unfamiliar with the domain.

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% for the single parameter 'object', and the description itself does not mention or explain this parameter. The schema's title provides some context, but the description adds no clarity about how to specify the object or what values are valid, failing to compensate for the low coverage.

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 computes a do-no-harm metric using silhouette IoU against a stored baseline, which distinguishes it from other feedback tools like feedback-quality or feedback-silhouette. The verb 'metric' and specific resource ('current form vs baseline') make the purpose clear, though the technical jargon might be opaque to some agents.

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?

It mentions it is read-only and a do-no-harm metric, which implies safe usage, but it does not explicitly state when to use this tool versus alternatives like feedback-silhouette or feedback-capture. There is no mention of prerequisites (e.g., having an intake baseline) or exclusions, so guidance is implied but not explicit.

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