preview_message

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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description adds crucial behavioral details: it explicitly states the tool is a preview, generates different wording each time, and requires no API key. These insights go beyond the annotations and set clear expectations.

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 well-structured with three focused paragraphs, but it contains some redundancy (e.g., repeating the preview nature in multiple places). It is not overly verbose, but could be tightened while maintaining clarity.

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 covers the tool's purpose, side effects (none), usage context, and generative behavior. It also notes the absence of an API key requirement, making it self-contained. No output schema exists, so return details are not expected.

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 already provides 100% coverage with descriptions for all parameters (name, role, company). The main description only restates that role and company are optional, adding no new semantics beyond what the schema already offers. Hence, it stays at the baseline of 3.

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 action and resource: 'Draft a sample AI-personalised outreach message for a named person.' It distinguishes from siblings by explicitly noting it's a preview and not sending anything, making its purpose unmistakable.

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 provides explicit guidance: 'Use it to check tone before committing to a sequence.' It also clarifies when not to use it (nothing sent, saved, or attached) and that the person need not exist as a lead, which helps in selecting this tool over alternatives.

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