fix_accessibility

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

With no annotations provided, the description carries the full behavioral burden, and it does so thoroughly. It discloses safety and side-effect behaviors: dry_run returns an identical report without touching the file, auto-backup writes to .ks4w-backups with backup=False skipping rotation only, saves are atomic and validated, and open-in-Word documents are refused. Per-category refusal conditions and human-review outputs are also spelled out.

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 long but every sentence earns its place; complex per-category behavior is organized into a clear scannable structure with code identifiers. The main operational contract is front-loaded, followed by category details and then safety/backup behavior, with no filler or repetition.

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 complex 8-parameter repair tool with no annotations, this description is remarkably complete. It covers what each category does, when it refuses, what reports contain, dry-run behavior, backup behavior, and document-lock constraints. Since an output schema exists, detailed return-shape documentation is unnecessary, and nothing essential for correct invocation is missing.

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 0%, so the description must compensate, and it does. Every category parameter (alt_text_placeholders, heading_skips, table_headers, doc_title) is explained with concrete behavior, heading_strategy's two values are named, and dry_run and backup semantics are described directly. Only file_path is left implicit, which is acceptable for an obvious parameter.

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 ('Repair'), resource ('audit_accessibility findings'), and mechanism ('one opted-in category at a time'), making the tool's function immediately clear. It also distinguishes itself from the sibling audit_accessibility by contrasting repair with detection, and the per-category details leave no ambiguity about scope.

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?

It explicitly frames usage in a workflow: 'audit -> fix -> audit' shows when this tool belongs after audit_accessibility. It also gives exclusions ('with none enabled the call refuses', 'Refuses documents open in Word') and names an alternative path for alt_text_placeholders via set_image_alt_text, so an agent knows both when to use and when not to use this tool.

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