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

Annotations already declare a non-read, idempotent, non-destructive mutation, and the description adds genuinely new context: one AI draft billed like the composer's Draft, the refusal conditions, and 'Nothing is sent.' The remaining gap is what happens to any existing draft text on the step — overwrite versus append is left implicit.

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?

Dense but front-loaded: purpose first, then refusals, then the safety note, then parameter roles and retry guidance. The parenthetical billing comparison to 'the composer's Draft' and the internal name 'Sergio' add slight noise but carry real product semantics.

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?

For a three-param mutation with no output schema, the description covers cost, eligibility, side effects, and idempotency, which is most of what an agent needs. It stops short of saying what the call returns (the rewritten text, a job id, or just success) and whether an existing draft is replaced.

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 only 33% (only idempotency_key is documented inline), yet the description compensates: task_id is the lead (read entity tasks) and step_id is the step id from the lead's journey, plus explicit retry guidance to reuse the same idempotency_key. That adds real meaning beyond the schema for the two undocumented UUID/string params.

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?

States a specific verb and resource: rewrites the text of a lead's upcoming step that a person sends, drafted from the conversation so far. The qualifier 'that a person sends' plus the refusal list cleanly separates it from edit_lead_step (manual edit) and create_draft, so an agent can pick it without opening schemas.

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?

Gives concrete when-not conditions: refused for a call step, a step Sergio sends on its own, or a step already past. It also clarifies that nothing is sent, so the agent knows this is a safe draft-only action. It does not explicitly name edit_lead_step as the manual alternative, which keeps it from a 5.

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