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

The description adds valuable behavioral context beyond the annotations: it explicitly states the tool uses only buyer-supplied facts (no external research), returns a draft for human review, and requires explicit wallet authorization for payment. The annotations already declare destructiveHint=true (likely indicating side effects like charging), and the description's payment note aligns with that. It doesn't contradict the annotations. It could have elaborated on the destructive hint, but overall it provides meaningful operational transparency.

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 primary purpose front-loaded in the first sentence, followed by usage constraints, output nature, and pricing. Each sentence earns its place—no fluff. It could be slightly more structured (e.g., separating pricing into a distinct block), but the information flow is logical 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?

Given the tool's complexity (nested input object with three subfields, plus four other parameters, no output schema), the description is incomplete. It fails to explain how to populate input.brief, input.audience, and input.source_text, nor does it describe the purpose of result_expires, idempotency_key, result_signature, or payment_signature. The only operational detail is the price and payment authorization. An agent lacks guidance on making a correct call, especially around payment and result retrieval, so the description is insufficient for correct invocation.

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 for the lack of parameter information. However, it does not explain any of the five parameters (input, result_expires, idempotency_key, result_signature, payment_signature). It only indirectly references the input via 'supplied facts' and mentions payment, but does not clarify the purpose of parameters like idempotency_key or result_signature. An agent would be left guessing how to construct the request correctly, especially the payment and result-handling 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 ('Write'), a resource ('a complete article'), and explicit constraints ('based only on supplied facts', 'with headings and an actionable conclusion'). This distinguishes it from sibling tools like blog_brief (which likely produces a brief, not a full article) and ad_copy or social_posts. The purpose is unambiguous and actionable.

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 specifies when to use this tool: when the buyer supplies facts and no external research is desired ('Uses buyer-supplied information only; no external research or outbound actions'). It also clarifies it returns a draft for human review. However, it does not explicitly name alternative tools or state when not to use it, so it lacks explicit exclusion criteria. The usage context is clear enough for an agent to decide, but not exhaustive.

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