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

With annotations already covering safety (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description adds real behavioral context: it never sends, it persists into the farm's Email Assistant and pre-fills the QuailOS reply box, it returns a draftId, and it requires Owner/admin read/write AI keys. These are non-obvious side effects and auth requirements not derivable from 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?

Four compact sentences with the key facts (draft, never sends, where it lands, return value, auth) front-loaded. Dense but each sentence carries information; only minor tightening is possible.

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 7-parameter mutation tool with no output schema and full schema coverage, the description supplies everything an agent needs: the side-effect surface, the return value (draftId), the auth requirement, and the recipient constraint.

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 the schema already documents all seven parameters including defaults and constraints. The description restates the recipient default and participant rule but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 (create) and artifact (reply DRAFT) scoped to an Email Assistant conversation, and immediately negates the obvious confusion with 'Never sends.' An agent can distinguish this from send_email without opening either schema.

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?

Clarifies the core condition (draft, not sent) and points at the downstream alternative by noting the returned draftId is 'usable with send_email.' It also states the recipient default and participant constraint. It stops short of an explicit 'use this when you want to stage a reply rather than send one' rule, so it is strong but not fully prescriptive.

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