Entity coverage audit

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well established. The description adds meaningful value beyond annotations: it explicitly discloses that the tool performs heuristic detection and deliberately avoids inventing missing entities — useful behavioral transparency about the heuristic/abstention behavior that annotations cannot 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?

The description is a single concise sentence that delivers the core purpose plus the heuristic-detection differentiator. No fluff or redundant phrasing. It could slightly improve by front-loading the noun/verb structure more explicitly, but it is efficient and 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 read-only audit tool with strong annotations (safety profile fully covered) and no output schema, the description covers the core behavior: checking primary/related entities, returning heuristic detections, and warning against invented entities. Given there's no output schema to explain return format, the description could describe what the audit output contains, but the core usage contract is adequately specified for a moderate-complexity 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?

Schema description coverage is only 33% (only 'url' has documentation), leaving primary_entity and related_entities undocumented in the schema. However, the description partially compensates by clarifying that related_entities is an explicit list checked against the page. It doesn't add richer detail about entity format, how primary vs. related entities are treated differently, or what the returned detected entities look like.

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 verb (check/audit) and resource (primary entity + related entities against a page), and distinguishes the tool's value by noting it returns 'heuristically detected entities without inventing missing ones.' It identifies what it does and its key differentiator, though it doesn't explicitly distinguish from specific sibling tools like aeo_intent_coverage.

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 usage context (auditing a page's entity coverage) but provides no explicit when-to-use guidance or exclusions. It doesn't name alternative tools or state when NOT to use this tool versus siblings like aeo_intent_coverage or aeo_audit_page. Some guidance is implied by the tool's naming and position among aeo_* siblings, but no explicit direction is given.

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