Draft a reply

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

Annotations mark readOnlyHint=false and destructiveHint=false, so creating a draft is already implied as a mutating but non-destructive operation. The description adds genuinely useful behavior beyond the annotations: it preserves 'thread and recipients,' explicitly states it does not send, and recommends reading the original message first for correctness. This provides valuable behavioral context without contradicting the annotations.

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 only two sentences, front-loads the primary action, then states the critical caveat ('Does NOT send') and a useful workflow recommendation. Every sentence earns its place with no fluff or repetition.

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 tool with 3 simple parameters, no output schema, and no nested objects, the description covers the essential points: what it does, what it does not do, and the recommended prerequisite. It is complete enough for correct invocation. A minor gap is not explicitly distinguishing reply_draft from the sibling create_draft, but the 'existing message' framing largely handles this.

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 100%, so parameters are already documented: message_id is 'the message to reply to,' body is 'plain text,' and reply_all has a default of false. The tool description adds no extra per-parameter detail beyond the schema, so the baseline of 3 is appropriate. The 'keeping its thread and recipients' phrase hints at reply behavior but doesn't add parameter-level semantics.

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 states a specific verb and resource: 'Create a draft reply to an existing message, keeping its thread and recipients.' It also adds the key exclusion 'Does NOT send,' which distinguishes it from send_draft and clarifies its scope relative to generic create_draft.

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 gives clear context: use this when replying to an existing message, and it explicitly warns 'Does NOT send' so agents know not to expect sending to occur. It also gives a concrete pre-step: 'Read the message with get_message first.' However, it does not explicitly name alternative tools like create_draft or send_draft for comparison, so it falls just short of full guidance.

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