Plumb · fit

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

Annotations already declare readOnlyHint and idempotentHint. The description adds behavioral context: the tool is called repeatedly with rendered data from the agent's build tags, expects convergence, and returns scores and fixes. It warns about stalling and advises reading deltas and coverage. This goes beyond annotations.

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 structured numbered list that is easy to follow. It is somewhat verbose but each sentence serves a purpose: defining the loop, input requirements, output fields, and expected behavior. Minor redundancy could be trimmed, but overall efficient for the complexity.

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 has 9 parameters, nested objects, no output schema, and is part of an iterative process, the description covers the essential workflow, input expectations, and output interpretation. It mentions the key return fields (score, done, topFixes, bar, instruction) and hints at deltas/coverage. Lacks explicit output structure details but sufficient for the iterative use case.

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 coverage is 100%, so the schema documents all parameters. The description adds value by explaining the rendered parameter shape is the same as plumb_verify, and how the iteration parameter sharpens coaching. This semantic linking helps the agent understand data flow.

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 is a 'self-healing build loop' for iterative pixel-perfect matching, distinct from one-shot checks. It names the verb 'iterate' and identifies the resource as visual builds. It differentiates from the sibling plumb_verify by emphasizing iteration.

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 explicitly says to use this for iterative refinement instead of a one-shot check, implying when-not-to-use. It provides a step-by-step loop. However, it does not explicitly list alternative tools or exclusion criteria beyond the contrast with one-shot checks, which are implied to be plumb_verify.

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