Plumb · audit

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds value by explaining that it is heuristic, reports only failures, and a clean result does not imply full accessibility. This provides behavioral context 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 single paragraph that efficiently conveys purpose, usage, and limitations. It is well-structured but slightly verbose with examples of checks; still, every sentence adds value.

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 no output schema, the description explains what findings contain (note + raw data) and limitations. With only one parameter and good annotations, the description is fully self-contained.

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 parameter 'doc' is described in the schema as 'A full PdsDocument object', but the description adds specificity: 'pass the raw JSON response from a prior plumb_node/plumb_outline/plumb_query call', clarifying the expected format and origin.

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 the tool performs a heuristic accessibility audit over a PDS snapshot, specifying the checks (text contrast and touch-target size). It distinguishes itself from sibling plumb_* tools by focusing on audit, not extraction or manipulation.

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?

Explicitly states when to use: after getting a PDS snapshot from plumb_node/plumb_outline/plumb_query. Also mentions what it does not do: it is not a certified WCAG audit, heading-order/missing-alt-text checks are missing, and it reports only failures.

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