Prepare an approval-gated AEO autofix

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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description aligns with these: 'always requires approval; it never publishes' reinforces the read-only safety profile. The description adds clarity about the approval gate and non-publishing behavior that annotations don't fully convey.

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?

A single dense but complete sentence covers purpose, authorization gate, and constraints. It's front-loaded and every clause earns its place. Slightly dense but efficient.

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 8 parameters and only 25% schema description coverage, the description could be richer, but the tool is structurally simple (no nested objects, no output schema, and the schema's one required param 'url' is self-describing). The 'optional apply caller-supplied replacements' phrase covers the main customization path. Given the modest complexity and good annotations, the description is reasonably complete.

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 only 25%, so the description must compensate. It explains that replacements correspond to caller-supplied 'exact' matches in the latest WordPress content, tying to content_html and proposed_changes semantics. However, it doesn't elaborate on current_year, primary_entity, or related_entities, leaving the other 75% undocumented.

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 gives a specific verb+resource ('audit a public page, then optionally apply replacements') and clearly states it returns a diff. It distinguishes from the many sibling scan/audit tools by emphasizing the apply-replacements and approval-gated behavior. Clear and distinct.

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 implies it's for when you need approval-gated fixes that go beyond scanning — it never publishes and always requires approval. However, it doesn't explicitly contrast with siblings like aeo_prepare_wordpress_fixes or aeo_audit_page, so an agent isn't clearly told when to prefer this over those.

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