a11y-toolkit: DOCX accessibility screening

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so safety is covered. The description adds real value beyond them: it is a zero-dependency *structural* pass only, it cannot replace a human review, and it advertises a `limits` field in the response so the agent knows the output self-documents its blind spots.

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?

Front-loaded with the purpose and the concrete checks, and the return-shape sentence at the end is useful. Minor flourish ("the other half of enterprise paperwork", "finds what makes it pointless") costs a little density but the substance is all present.

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?

With no output schema, the description compensates by listing the returned JSON keys (mode, language, images, tables, findings, summary, limits). Combined with the enumerated checks and the explicit human-review caveat, an agent has enough to call it correctly; only per-parameter behavior of `lang` is left unstated.

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 coverage is 100%, so `path` and the `lang` enum are already fully documented in the schema. The description reinforces the local-file constraint for `path` but says nothing about what `lang` changes in the output (finding text localization). Baseline 3 is appropriate.

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 resource (.docx) and enumerates exactly what the pass checks: missing alt text (docPr without descr), fake headings, document language, and tables without a header row. This makes it trivially distinguishable from the PDF/DOM/URL audit siblings, which operate on different inputs.

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?

"LOCAL .docx" implies a file-path precondition and "Full review needs a human" signals this is a screening step, not a verdict. However, no sibling is named as the alternative (e.g., a11y_audit_pdf for PDFs, a11y_autofix for remediation), so routing is left to inference.

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