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

The description explicitly states that no messages are sent, that it uses buyer-supplied information only with no external research, and that the output is a draft for human review. It also mentions the payment requirement and price. This goes well beyond the annotations, which only indicate non-readOnly and destructive, and contradicts none.

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?

Four concise sentences, front-loading the core value (what it drafts and that it sends nothing), then clarifying constraints. No fluff, and every sentence provides essential information for an agent deciding whether to call it.

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 (5 params, nested objects, no output schema), the description covers key behavioral aspects: draft only, no sends, no research, payment needs. It does not detail the output format or what the draft will contain beyond 'message purpose and stop rules', but that is central enough. It is nearly complete, with a minor gap on return format.

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 coverage is 0% (no descriptions in the schema), so the description must compensate. It does mention input is 'buyer-supplied information' and that no external research is used, hinting that 'brief' and 'source_text' are the primary content inputs. However, it does not explain the roles of 'audience', 'result_expires', or the signature parameters. With 0% coverage, the burden is higher, so a 3 is fair.

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 ('Draft'), a clear resource ('bounded follow-up sequence'), and explicit scope limits ('with message purpose and stop rules; no messages are sent'). It is easily distinguished from sibling tools like tradepilot_service_outreach_email_draft or tradepilot_service_followup_email_draft, which draft individual messages rather than a sequence.

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 clearly states the tool only uses buyer-supplied information and performs no external research or outbound actions, implying it is for drafting only. It does not explicitly name alternative tools, but the scope (sequence vs. single message) is implicit. It also notes the price and payment requirement, which guides whether to invoke it.

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