Complete AI-search page audit

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

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true, covering the safety profile (non-destructive, idempotent). The description adds the scope of checks run and the 'one public page' constraint and that it produces 'an extractive answer preview' with 'citable chunks,' giving the agent context on what the run examines without contradicting 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?

One dense sentence, front-loaded with the strongest signal ('Complete AI-search page audit'), then a compact enumeration of all checks. Zero filler, every clause earns its place.

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 6-parameter tool with no output schema, the description enumerates the checks but leaves the parameters' roles ambiguous. The agent can infer primary_entity/related_entities/expected_intents/candidate_links/candidate inputs from the enumerated checks, but the schema provides little documentation and the description doesn't clarify parameter interplay or required inputs beyond url. Given optional parameters with defaults, the description is adequate but not 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 description coverage is only 17%, and the schema itself documents almost none of the parameters well (url has 'Public webpage URL', others rely on type/enum/defaults only). The description adds no parameter-level detail beyond vague category names like 'entity coverage' and 'intent coverage' that map loosely to primary_entity/related_entities and expected_intents. This is a real gap for 6 parameters, so a baseline 3 with description partly compensating but not fully is appropriate.

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 has a specific verb ('Run') and names 9 distinct check categories (readability, entity coverage, citation readiness, intent coverage, extractive answer preview, citable chunks, internal linking, schema, freshness) on 'one public page.' This clearly distinguishes it from the many sibling aeo_* single-purpose audit tools (e.g., aeo_ai_readability_audit, aeo_entity_coverage) which each do only one of these checks, making this the comprehensive/combined audit.

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 implicitly signals this is the 'complete' or bundled audit versus the granular sibling aeo_* tools, recommending it when a full comprehensive audit is desired. It doesn't explicitly state when NOT to use it or name alternative granular tools, but 'Complete AI-search page audit' and the enumerated checks make the use case clear for a page-level assessment.

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