a11y-toolkit: Disprover: re-verify findings

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

Annotations already mark this as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context: it re-runs the live audit, rejects non-reproducing findings with a reason, and catches false positives/race conditions/page changes. No contradiction with 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?

Four compact, front-loaded sentences cover action, purpose, output, and usage instruction. Every sentence earns its place with no redundancy or filler.

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?

The description provides the core purpose, output summary, and usage context. Since there is no output schema, it doesn't fully specify the exact structure of confirmed/rejected findings, but it gives enough high-level information for an agent to invoke the tool 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%, and each parameter already has a clear description. The main description doesn't add per-parameter details, so it stays at the baseline 3 without needing to compensate.

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?

States a specific verb (re-runs, marks) and resource (audit findings against the live page), and explains the output (fresh score over confirmed findings). It clearly distinguishes the tool from sibling audit and autofix tools by framing it as the verification/disproval step.

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 tells the agent when to use it: 'Run this before acting on any audit report.' It gives clear context for invocation, though it doesn't name alternative tools or state explicit when-not-to-use conditions.

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