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

The description states 'no external research or outbound actions', which directly contradicts the annotation openWorldHint=true, which typically indicates the tool may access external data. This is a clear contradiction. While the description does disclose payment requirements (destructiveHint), the contradiction forces a score of 1.

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 three sentences, front-loaded with the core purpose, and includes essential constraints (no external research, draft output, price, payment). Every sentence adds value with no redundancy or fluff. It is well-structured and easy 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?

The tool has five parameters, a nested object, no output schema, and annotations that partially conflict. The description covers the purpose, constraints, and payment, but omits any explanation of the input parameters or the output format beyond 'a draft for human review'. Given the complexity, this is incomplete. The contradiction with openWorldHint also reduces completeness.

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%, so the description must compensate by explaining parameters. It does not mention any of the five parameters, including the required 'brief' or optional ones like 'idempotency_key' or 'payment_signature'. The only hint is 'Uses buyer-supplied information only', but that is insufficient to guide an agent on how to populate the schema. The description fails to provide any parameter semantics.

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 verb ('Produce') and resource ('headlines'), and details the output format ('grouped by angle, with rationale and unsupported-claim checks'). It clearly distinguishes this tool from siblings like email_subject_lines by focusing on headline generation for a workshop. The scope is explicit and unambiguous.

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 provides clear context for when to use the tool: it uses buyer-supplied information only and performs no external research or outbound actions, implying it is appropriate when the buyer's input is sufficient. It also notes the result is a draft for human review, signaling it's not a final output. However, it does not explicitly name alternative tools or state when not to use it, leaving some room for inference.

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