feedback-readiness

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

With no annotations, the description carries the full burden. It discloses that the score is order-free (order-independent) and deduped, and that it does not use a judge or images, which are useful behavioral traits. Still, it lacks details such as side effects (likely none), behavior with defaults, error conditions, or the exact output structure beyond 'fraction.'

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, efficient sentence that packs in key qualifiers without fluff. It is front-loaded with the core purpose and includes qualifiers but omits details that are better conveyed elsewhere. Slightly above average because it uses space effectively, though a tad cryptic.

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 that the tool has two optional parameters and no output schema, the description provides a foundational idea (readiness fraction) but does not specify what the actual returned value looks like (e.g., a number, a list of gate statuses). It also doesn't explain 'order-free' or 'deduped' icons in the context, leaving some ambiguity about the exact scoring mechanics.

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 description gives no guidance on the two parameters ('object' and 'asset_class'). Schema coverage is 0%, and while the schema includes titles like 'Mesh object to score (defaults to active)', it does not explain how these inputs affect the scoring or how to choose asset_class values, leaving the agent without crucial semantics.

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?

Clearly identifies the tool as a 'scorecard' that reports the fraction of all objective gates passed, with qualifiers 'order-free + deduped' and 'no judge, no images' that distinguish it from visual feedback tools. It uses a specific noun ('scorecard') and describes the resource type, but lacks an explicit action verb like 'compute' or 'report'.

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 offers implied guidance: it is the 'objective' scorecard without judge or images, suggesting it should be used for automated readiness checks. However, it does not explicitly name alternative tools (e.g., feedback-capture, feedback-lookdev) or state when not to use it, leaving some ambiguity about selection.

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