create_draft

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

There are no annotations, so the description carries the burden of behavioral disclosure. It does disclose the critical non-sending behavior, but it does not mention whether the draft is saved/persisted, what the response contains, or any permissions/side effects. It adds some value but not complete transparency.

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?

A single sentence that front-loads the action and then gives the two most decision-relevant facts: the field set matches send_message and the message will not be sent. No filler.

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 seven-parameter tool with no annotations and no output schema, the description is lean. It relies on the agent knowing send_message's field semantics, and it does not describe return values or whether draft creation modifies anything beyond creating a draft. This is adequate but leaves gaps for an agent invoking it independently.

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 description coverage is only 14%, so the description needed to compensate. It names reply_to_message_id and defers the rest to 'same fields as send_message,' which is a useful pointer but does not explain the semantics of the six other parameters. The parameter names are mostly self-explanatory, but the description adds little per-field meaning.

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 opens with the specific action 'Create a draft' on a message resource, and immediately contrasts it with send_message by stating it 'Does not send.' This clearly differentiates it from the sibling send_message tool.

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 explicit 'Does not send' sets the primary selection criterion: use this when a draft is needed rather than an immediate send. It references send_message's field set as the format to reuse, though it does not give an explicit when-not-to-use or alternative.

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