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

With no annotations, the description carries the full burden and does disclose real behavioral traits: static rules only, no rendering, and no quota consumption. It does not say whether the scan is synchronous or how results are retrieved (get_report exists as a sibling), leaving a modest gap.

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?

One sentence with the action front-loaded and the behavioral caveat in a compact parenthetical. Nothing is redundant and nothing is buried.

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 single-parameter audit tool with a fully documented schema and no output schema, the description covers purpose, input mode, and the key behavioral constraints (no render, no quota). It falls short only on how findings are returned relative to the get_report sibling.

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?

There is a single parameter with 100% schema description coverage ('HTML source, max 512KB'), so the schema already carries the semantics. The description adds only the 'pasted' framing and no format or encoding detail beyond the schema — the baseline 3 for high coverage applies.

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 ('Audit') and resource ('pasted HTML markup') plus the target standard (WCAG violations). The word 'pasted' implicitly separates it from the sibling scan_url, which handles remote content, so an agent can route correctly without opening a schema.

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 makes the input mode clear ('pasted HTML') which implies the alternative is scan_url, but it never names scan_url or states the condition for choosing between them. Usage is implied rather than explicit, with no when-not guidance.

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