Prepare corrected WordPress content

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, setting a strong safety baseline. The description adds value by clarifying the tool returns 'exact changes and unresolved items for review' (a non-destructive, review-oriented workflow) and explicitly frames it as a prerequisite step before a separate publishing action. This complements rather than repeats the annotations.

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?

Two sentences, zero filler. Each clause earns its place: the action ('prepare'), the scope ('duplicate H1s and alt text'), the non-publishing constraint, the output ('exact changes and unresolved items'), and the integration point ('before the WordPress MCP updates'). Front-loaded with the most critical information first.

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 review-oriented preparation tool with strong annotations (read-only, non-destructive, idempotent) and high schema coverage, the description covers the essential workflow: what it fixes, that it doesn't publish, and that it returns reviewable output. Since there is no output schema, the description's note about returning 'exact changes and unresolved items for review' partially compensates. A slight gap: it doesn't clarify what happens with unrecognized issue_codes or how the theme_renders_title_h1 flag interacts with the H1 fix, but given the tool's preparation-only nature, this is acceptable.

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 80% (4 of 5 parameters have descriptions in the schema). The description adds the key context that content_html should be the 'Latest WordPress post body HTML' and that issue_codes like 'multiple_h1' or 'image_missing_alt' are expected values, plus clarifies image_alt_texts maps alt text to specific image URLs. However, the description doesn't explain the relationship between issue_codes and the specific fix behavior, leaving some added value unrealized. Baseline 3 is appropriate given high schema coverage and modest description add-ons.

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 uses a specific verb+resource combination ('prepare corrected WordPress post HTML') with clear scope ('duplicate content H1s and missing or empty image alt text'). It clearly distinguishes itself from publishing tools by stating 'do not publish' and 'before the connected WordPress MCP updates the post', and contrasts with the sibling tool aeo_autofix_page which implies direct application.

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 explicitly states this is a preparation step ('Prepare, but do not publish') and indicates it should be used before the WordPress MCP update, establishing clear context. However, it doesn't explicitly name alternative tools or describe when NOT to use it versus aeo_autofix_page, which appears to be the closest sibling that actually applies changes.

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