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

The description contradicts the annotations. It states 'Uses buyer-supplied information only; no external research or outbound actions' and 'Returns a draft for human review', implying no side effects and no external data access. Yet annotations have openWorldHint: true (may use external knowledge) and destructiveHint: true (may have destructive side effects). This is a clear inconsistency that undermines trust, so behavioral transparency fails despite the description's own disclosures.

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 concise, with the core purpose front-loaded in the first sentence and additional constraints in the second. It also includes pricing and payment authorization notes, which are relevant but not over-explained. No wasted words, and it is easy to scan quickly.

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 5 parameters, a nested object, no output schema, and no parameter descriptions. The description does not explain what the returned draft looks like, how missing fields are reported, or how the input fields are used. It only says 'Returns a draft for human review', which is too vague. Given the complexity, the description should detail output structure and field roles, but it does not.

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 0% and the description does not explain any of the five parameters or the nested object. It mentions 'from supplied facts' but doesn't map that to specific fields like 'brief', 'source_text', or 'audience'. The agent must infer parameter purposes from names alone, which is insufficient for a tool with nested structures and additional payment-related fields.

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 a specific verb+resource: 'Suggest JSON-LD structures' and 'list required missing fields'. It also adds constraints ('do not fabricate ratings or reviews') and clarifies it uses only buyer-supplied information. This distinguishes it from the many sibling tools (e.g., entity_extraction, text_classification) that handle other data types.

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 conveys a clear usage scenario: when you have facts and need JSON-LD structured data for a page, with the output being a draft for human review. It also states what it does NOT do ('no external research or outbound actions'), giving some boundary. However, it does not explicitly name alternative tools or conditions when not to use it, leaving some inference to the agent.

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