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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: the draft's status is never mutated and unsupported email types (sent/scheduled emails, inbound replies, sequence templates) are rejected. It stops short of describing auth requirements or the response shape.

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 sentences, zero filler, and the core action plus its at-least-one-field constraint lead. The negative guarantees follow and each sentence earns its place by preventing a distinct misuse.

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 three-parameter edit tool with full schema coverage and non-destructive annotations, the description covers the action, constraints, and side-effect profile adequately. With no output schema present, a brief note on the return value would close the only remaining gap.

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%, so the individual fields and their minLength are already documented, which sets a baseline of 3. The description adds a real constraint not encoded in the schema: at least one of subject/body must be supplied, plus a non-empty requirement for whichever is provided.

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 (edits) and resource (subject and/or body of an AI reply draft) with a clear scope boundary ('before it goes out'). It implicitly separates itself from send_reply_draft by explicitly noting it never sends, so an agent can route correctly without opening sibling schemas.

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?

Gives explicit preconditions ('provide at least one field; provided fields must be non-empty'), states what the tool will never do, and names the alternative path (a human sending from the app, or send_reply_draft). It also enumerates what is refused, which is exactly the when-not guidance an agent needs.

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