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

With no annotations, the description fully discloses behavior: it uses only the site's own text, owner's published facts, or measurements, with 'no language model wrote any of it'. It also states that unbuildable patches are 'skipped and counted rather than guessed', and that it is 'deterministic and read-only' on the provider's side—valuable beyond the schema.

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 dense but organized: it starts with the purpose, then details patch types, then gives action steps and constraints. Every sentence adds information—no wasted words. It's longer than the typical tool description but earns its length, though it could benefit from slight formatting for readability.

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?

Given the absence of an output schema and annotations, the description adequately explains the return value (patches) and usage (apply and re-run audit). It covers constraints and provenance but doesn't detail the exact patch format or error handling. Still, it's sufficiently complete for an agent to invoke and act on the tool.

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 schema already documents 'domain' at 100% coverage. The description adds the constraint 'Claimed domains only' and clarifies that the tool works on 'a cataloged domain', providing context beyond the schema definition. This enriches the single parameter's meaning without overcomplicating it.

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 clearly states the tool returns 'paste-ready patches' generated from 'Grounded AEO' measurements, listing specific patch types (title/meta blocks, robots.txt Allow lines, JSON-LD, /llms.txt). This distinguishes it from sibling tools like check_aeo_record or generate_free_record, which focus on checking or free records, not applying fixes.

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 says 'USE THIS TO ACT: if you have write access to the site's codebase, apply each patch... then re-run run_audit to confirm.' This gives a clear 'when to use' context. It doesn't name alternative tools for when not to use, but the action-oriented guidance implies this is the post-audit tool.

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