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

Adds real value beyond the annotations: nothing is sent, saved, or attached; no API key required; output is non-deterministic ('same input yields different wording each time'); and it returns the drafted text. The non-determinism is in mild tension with idempotentHint=true, but since the tool mutates no state the hint still holds in the side-effect sense.

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?

Front-loaded with the preview framing and the 'nothing is sent' constraint, then the caveats. Three short paragraphs with no filler, though the trailing-space line breaks and the API-key note make it slightly longer than strictly needed.

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?

With no output schema, the description correctly states the return ('the drafted message text') and covers safety, auth, and determinism. For a simple 3-param generative tool this is close to complete; only an indication of length/format of the draft is missing.

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 100%, so the schema already documents name/role/company with lengths. The description only restates that role and company are optional, adding no format or semantic detail beyond the schema. Baseline 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?

Specific verb+resource: 'Draft a sample AI-personalised outreach message for a named person.' It immediately frames the operation as a preview rather than a send, which separates it from send_to_campaign and the many lead-mutation siblings.

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 a clear use context ('Use it to check tone before committing to a sequence') and a precondition the agent would not otherwise guess ('The person does not need to exist as a lead'). It does not explicitly name send_to_campaign or other alternatives, so it stops short of a full when/when-not statement.

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