scorecard

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

With no annotations, the description carries full behavioral burden and does it well. It discloses that recording is a 'claim about work already done', not the action itself, and explains the side effect on `export` (adds a reminder if revision is not covered). It also clarifies the semantic of pass/fail outcomes. This goes beyond what an annotation could provide.

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?

Despite being ~140 words, every sentence contributes. The purpose is stated first, followed by verdict semantics, then the export interaction, and a closing note on re-judging. It is structured with paragraphs and clear separation of ideas, front-loads the critical 'never call without' warning, and avoids redundancy. Appropriate length for the behavioral nuance it conveys.

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?

For a 2-parameter tool with no output schema, the description covers all necessary context: the action's role in the judge workflow, prerequisites (actual previews), the meaning of each verdict, the interaction with `export`, and the policy for re-judging. An agent has everything it needs to decide to call and to use parameters correctly.

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 100%, so the baseline is 3, but the description adds significant semantic depth. It elaborates the meaning of 'pass' and 'fail' with specific threshold criteria (each axis ≥ 8) and clarifies that `revision` must be the id whose renders were previewed. This explains the purpose of both parameters beyond their schema types.

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 opens with a precise verb-resource pairing: 'Record the verdict of a judge loop you have COMPLETED for a revision.' It explicitly names the tool's role as the final step of the `judge` skill and distinguishes it from siblings by referencing its relationship to `export`. No ambiguity about what the tool does.

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?

Provides explicit conditions for use: 'never call this without having scored the axes against actual `preview` renders.' It also instructs when to record a new scorecard ('Judging again after further edits? Record a new scorecard'), and explains the consequence of not covering a revision in `export`. Clear when-to-use and when-to-refrain guidance.

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