create_reply_draft

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

With no annotations, the description carries the full burden. It does disclose two behaviors: the draft is visible (opened in Mail) and nothing is sent, which is the key non-destructive signal versus send_email. It omits permission requirements, what happens if a draft already exists, and what the call returns.

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?

Three short sentences, zero waste, with the operation, the addressing rule, and the non-send guarantee front-loaded in that order. Every sentence earns its place.

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 draft-creation tool with no annotations and no output schema, the description covers the essentials (what it makes, what it doesn't send) but says nothing about the result — draft id, where it lands, or failure modes. Adequate but leaves real gaps for an agent verifying success.

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 all four parameters including the INBOX default are already documented in the schema. The description adds one useful semantic note — that the original message determines recipient and subject (i.e., message_id drives addressing) — but no format or syntax detail beyond that. Baseline 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?

States a specific verb and resource: open a reply draft for an existing message. 'Reply' implicitly separates it from the sibling create_draft (a fresh draft), but it never names that sibling, so an agent must infer the distinction. Clear purpose without explicit sibling differentiation.

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 phrases 'for an existing message' and 'This does not send anything' imply the usage context (replying to an existing thread without sending), but no alternative tool is named and no when-not-to-use condition is given. Usage is implied rather than stated.

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