preview_message

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

No annotations are provided, so the description carries the burden. It discloses that it's a public endpoint with no auth, which is useful behavioral context. However, it doesn't describe the return format, whether it makes network calls, or any generation characteristics beyond the sample nature. The 'sample' qualifier hints it doesn't persist data, which is helpful context.

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 a single concise sentence that front-loads the core purpose and includes the auth note. It's efficient with no wasted words. Could arguably add a bit more usage context but is appropriately sized.

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 simple preview tool with 3 params (1 required), 100% schema coverage, and no output schema, the description is mostly adequate. It would benefit from noting what kind of output to expect (formatted text) and clarifying that this is non-persistent. The lack of output schema means the description could hint at the return format, but the tool's simplicity keeps the gap modest.

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 100%, and the description mentions that role and company are optional field inputs that personalize the message. The schema descriptions do carry the parameter meaning. The description adds the context that these are used to personalize the message, which is useful but minimal — 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?

The description clearly states the tool generates a sample AI-personalised outreach message for a person, with a specific verb ('Generate'), resource ('sample outreach message'), and scope ('for a person'). This distinguishes it from siblings like send_to_campaign and start_autopilot, though it doesn't explicitly name alternatives.

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 some context ('Public endpoint — no auth required') and indicates this is for generating a preview/sample, implying it's a non-destructive preview tool distinct from sending actions. However, it doesn't explicitly state when to use this vs alternatives or when not to use it.

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