audit_accessibility

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

With no annotations, the description carries the full behavioral burden and does so thoroughly. It discloses read-only semantics, the precise list of checks, a subtle contrast-detection rule ('skipped, not guessed when either side is absent'), and the output shape (location, fix hint, per-category counts, pass flag).

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 front-loaded with the key read-only and audit intent, then efficiently packs the full scope of checks and result details into a compact paragraph. Every sentence earns its place, including the final pointer to fix_accessibility.

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 tool with an output schema, the description is complete. It covers what is audited, how ambiguous cases are handled, what each finding contains, what the summary reports, and which sibling handles repairs. The existence of an output schema removes the need to describe the return structure in prose.

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 has only one parameter, file_path, with 0% schema description coverage. The tool description does not add any detail about accepted path formats, file types, or meaning. The parameter name is self-explanatory enough for basic invocation, but the description provides no additional semantic value beyond the schema.

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 names a specific verb ('Audit') and resource ('accessibility'), then enumerates the exact checks performed: heading hierarchy, image alt text, table header rows, contrast, document title, and generic hyperlink text. It also distinguishes itself from the sibling 'fix_accessibility' by explicitly marking this as read-only.

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 clearly implies this is the read-only auditing step and points to fix_accessibility for repairs ('fix_accessibility repairs opted-in categories'), giving the agent a natural when-to-use context. It does not, however, explicitly discuss when not to use it or contrast it with validate_document or other validation tools.

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