create_reply_draft

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

The description adds the key behavioral constraint that the tool never sends the email, which goes beyond the annotations (readOnlyHint: false, destructiveHint: false). It also clarifies the draft is for manual review. It doesn't mention potential side effects like overwriting existing drafts, but the core non-sending behavior is transparent.

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 a single sentence that is direct, front-loaded, and brief. It communicates the action and key caveat with no unnecessary words.

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?

The description covers the core purpose and the critical non-sending behavior, but with 0% parameter coverage in the schema, it does not fully specify how to use the parameters. It also lacks mention of prerequisites or error scenarios, though the presence of an output schema may cover return values.

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 0%, so the description must compensate. The phrase 'reply or reply-all' maps to the replyAll boolean, but the required parameters emailId, storeId, and body are not explained in the description, leaving their roles ambiguous beyond their names.

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 tool saves a reply or reply-all draft and explicitly notes it never sends the email. This distinguishes it from any sending tool and from sibling tools that search, read, or update emails, establishing a specific action and resource.

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 the tool is for creating drafts for manual review, and the 'never send it' caveat provides important usage context. However, it does not explicitly name alternatives or exclusion conditions, though no direct sending tool exists among the siblings.

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