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

Adds substantial context beyond the annotations: latency of two to four minutes, paid-account-only live search evidence, and that AI crawler access and page-date checks are unavailable for non-live sources. It does not clarify whether the call returns the audit inline or a job handle to be retrieved via get_result, which matters given idempotentHint=false and a get_result sibling.

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?

Purpose and output list are front-loaded, and the closing instruction to present the audit in full is useful. However, it is a single dense paragraph that bundles output shape, source selection, pricing tier, and latency together, making the key selection guidance harder to scan.

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 carries the return-value burden and does so well by naming the score, categories, issues, and recommendations. It covers the expensive, open-world run and its time cost; the only meaningful omission is whether results persist and are fetchable afterward.

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 the baseline is 3; the description still adds value by explaining the trade-off between url, draftId, and content and by noting targetQuery is optional and inferred if absent. It stops short of adding constraints like the 50000-character content limit, but that is already in the schema.

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 verb and resource ('Runs an AEO audit on one piece of content') and immediately enumerates what comes back: score out of 100, category scores, issues, recommended changes with proposed text. This is clearly distinguishable from siblings like create_draft or get_result, which operate on different artifacts.

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?

Gives an explicit decision rule for the three source modes, ranked ('url of a live page (best, because technical checks ... run only on a live page)'), plus the fallback instruction to ask the user when no source is given. It also explains when to supply targetQuery versus letting inference happen.

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