draft_message_to_contact

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

Annotations indicate the tool is not read-only (readOnlyHint=false), which aligns with drafting. The description adds the key behavioral point that no message is sent. However, it does not disclose what happens after drafting—whether the draft is saved, returned, or discarded—leaving ambiguity about side effects. More transparency about the output or storage would improve this.

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?

Two sentences with no redundant words. The first sentence states the action, the second clarifies a critical constraint. Information is front-loaded and every part contributes to understanding the tool.

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 fails to explain what the tool returns (e.g., draft ID, confirmation). For a common task like drafting, this omission reduces completeness. The description covers purpose and distinction but lacks result details. Considering the tool's simplicity, a 3 is reasonable.

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?

Input schema has 100% coverage with descriptions for both parameters. The description does not add new meaning beyond the schema; 'contactId' is described as 'Saved contact ID from list_my_contacts' in both places, and 'message' as 'Message text'. Baseline score of 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 action: 'Draft a message to a saved contact'. The verb 'draft' is specific and distinct from siblings like 'send_message_to_contact'. The additional sentence 'This does not send anything' reinforces the tool's purpose and differentiates it from send tools.

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 implies when to use this tool by stating 'does not send anything', suggesting it is for composing a message without sending. However, it does not explicitly mention alternatives or prerequisites like having a contact from list_my_contacts. The contrast with send_message_to_contact is clear but not named.

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