Content freshness audit

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered by structured data. The description adds value by disclosing that it flags content for 'human verification' and explicitly that it does not declare content incorrect—a non-obvious behavioral boundary. This is useful but modest extra disclosure beyond 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 crisp sentences, zero filler. Both sentences add distinct value: the first enumerates what gets flagged, the second explicitly clarifies a limitation. Front-loaded and 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?

The tool has no output schema, so the description bears some responsibility for explaining results. It clarifies the output is a set of flags for human review, not judgments—good. With two simple params (one required URI), generous annotations (readOnly, idempotent, openWorld), and a clear scope, the description is largely sufficient. A minor gap is the lack of explicit mention of the current_year param's role, but overall completeness is strong.

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 50%: the url param is documented ('Public webpage URL'), but current_year is not described in the schema either. The description adds no parameter-level detail beyond what the schema provides, so for the covered url param it's baseline. The undocumented current_year param in the schema is not compensated by the description, which mentions 'older years' generically but not the current_year input.

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 states a specific action ('Flag older years, relative time claims, pricing or limits, and dated screenshots for human verification') against a specific resource (content freshness). It clearly distinguishes from siblings like aeo_ai_readability_audit and aeo_entity_coverage by scoping to freshness/dated-content concerns. The verb 'flag' plus target categories gives a precise purpose.

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 explains what gets flagged and explicitly notes 'It does not declare flagged content incorrect,' which is a useful boundary. However, it gives no guidance on when to choose this over alternative audits (e.g., aeo_audit_page, aeo_ai_readability_audit) or when freshness auditing is inappropriate. No exclusions or alternatives named.

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