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

Annotations already indicate non-destructive and non-read-only. The description adds behavioral context: the message is stored as a draft with status 'pending_approval' and waits for review. This goes beyond annotations by describing the lifecycle step. No contradictions.

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 three sentences, front-loaded with the core action and key constraints. Every sentence adds value: the first states the action, the second clarifies the non-sending and status, the third provides next steps. No wasted words.

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?

Despite lacking an output schema, the description thoroughly covers what the agent needs to know: the tool creates a draft, the resulting status, and the follow-up tools (list_pending_approvals, approve_message). It also references sibling tools, fitting into a workflow.

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%, with each parameter described. The description adds meaning beyond the schema by explaining the purpose of custom_instructions (appended to step's ai_prompt, e.g., tone or angle). This helps the agent understand how to use the optional parameter effectively.

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 an AI personalized message draft for a specific campaign_contact and step, using the template and lead profile. It also explicitly distinguishes itself by stating what it does NOT do (the message is not sent; it is stored as a draft with status 'pending_approval'). This differentiates it from sibling tools like approve_message and save_lead_message.

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 context on usage: generate the draft, then use list_pending_approvals + approve_message to release it. It gives a clear workflow. However, it does not explicitly state when NOT to use this tool or list alternative tools for different scenarios.

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