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

The description discloses key behavior: it replaces the draft text, keeps it in the approval queue, and does not send it. It also imposes a factual accuracy constraint. While the annotations already indicate the operation is neither read-only nor safe from destructive changes, the description adds useful context by clarifying that the rewrite is not the final send step.

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 compact and front-loaded with the core action. It uses two sentences to convey purpose, usage guidance, and key constraints without unnecessary detail. The structure flows logically from what the tool does to how to use it effectively.

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 description provides sufficient context for the agent to use the tool correctly, including the prerequisite call to list_pending_outreach and the constraint not to invent facts. Since an output schema is present and the operation is straightforward, no additional explanation of return values or error handling is needed.

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?

The schema provides 100% coverage of all three parameters, including detailed guidance on the subject parameter's null semantics and the leadId's source. The description adds general context about using lead data but does not materially enhance the parameter-specific explanations already present in the schema, so the baseline score of 3 is appropriate.

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 action ('Replace the text of an outreach draft that is waiting for approval') and clarifies the intended use case ('fix copy that reads like a mail-merge'). It distinguishes the tool from siblings by explicitly noting that the rewritten draft 'stays in the approval queue' and 'is not sent by this tool.'

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 gives clear when-to-use guidance: use it when fix copy that reads like a mail-merge. It also tells the agent how to proceed ('get the draft and the lead's scoreExplanation from list_pending_outreach') and what not to do ('Do not invent facts'). It explicitly states the tool does not send the outreach, preventing confusion with send_outreach.

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