Accessibility audit

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

With no annotations, the description carries the transparency burden. It discloses a key limitation (color-contrast requires pixels and is not evaluated) and implies a read-only audit. However, it does not mention potential side effects, return format, or error behavior, which would be valuable for an agent to anticipate outcomes.

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, well-structured sentence with a parenthetical clarification. It is front-loaded with the main action and lists specific issue categories efficiently, with no redundant wording.

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 simple tool (one parameter, no output schema, no nested objects), the description covers the core functionality and limitations sufficiently. The lack of an output format hint is a minor gap, but the audit scope is clear and the parameter is fully documented.

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 input schema provides 100% description coverage for the single parameter (device_id with details on accepted formats). The description adds no parameter-specific semantics beyond the schema, so the baseline score of 3 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?

The description clearly states the tool audits the current screen for specific accessibility issues (undersized touch targets, unlabeled controls, duplicate labels), using a specific verb 'Audit' and resource 'current screen'. It differentiates from sibling tools like inspect_screen by focusing on accessibility checks rather than a general screen dump.

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 gives clear context for use (auditing accessibility of the current screen) and explicitly notes what is excluded (color-contrast checks). It does not name alternative tools, but the scope is clear enough to imply when to use it over general inspection tools.

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