Create a draft

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The description clarifies that the draft is not sent, which is a key behavioral trait, and it complements the openWorldHint by implying side effects (draft creation). However, it does not elaborate on other potential side effects (e.g., threading behavior via thread_id) or what the draft persistence entails, leaving some uncertainty.

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 exactly two sentences, front-loading the core purpose and usage condition. There is no redundant or filler content; every word earns its place. It is ideal for an agent to parse quickly.

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?

Given 8 parameters (4 required) and no output schema, the description is minimal but adequate for the core action. It does not mention return behavior, error handling, or prerequisites beyond what the schema states. The openWorldHint suggests potential side effects that are not disclosed, so the description could be more thorough, but it covers the essential intent.

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, so the baseline is met. The description adds no parameter-specific guidance beyond what the schema already provides; it simply states the overall action. It does not explain relationships between parameters (e.g., how thread_id interacts with 'to' or 'subject'), but the schema descriptions are sufficient for basic use.

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 uses a specific verb-resource pair: 'Save a draft' and clearly states the non-sending behavior. It distinguishes itself from send_message by explicitly noting when to use it ('whenever the user has not explicitly asked for the message to go out'), which differentiates it from sibling 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 provides an explicit when-to-use condition ('Use this whenever the user has not explicitly asked for the message to go out'), which is clear and actionable. It does not name alternative tools like send_message or reply, but the implication is strong enough for an agent to infer the correct selection.

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