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

Annotations only declare readOnly=false, destructive=false, openWorld=true. The description adds genuinely useful behavior: this never sends, the body must be plain text, write permission is required, and the draftId is the handle for subsequent edits. That goes meaningfully beyond the annotation set for a mutation tool.

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 compact clauses with the most important constraint ('never sends') front-loaded, followed by parameter sourcing and auth requirements. No filler sentences.

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, the description covers the critical behaviors, permission requirement, and even the returned draftId handle. Remaining gaps are minor field-level details like cc formatting and account selection.

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 0%, so the schema documents nothing. The description compensates for the two highest-value parameters (replyToMessageId, draftId) with sourcing and reuse semantics, and constrains body to plain text, but leaves to, cc, subject, and emailAccountId unexplained.

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 or update) and resource (mailbox draft) and immediately disambiguates from the sending sibling with 'never sends'. An agent can distinguish this from send_mail and create_draft without opening a 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?

Gives clear context: use for drafts kept for review, thread replies via replyToMessageId from read_thread, reuse the returned draftId for edits, and requires account write permission. It names the source of inputs and the follow-up path but does not explicitly say when to prefer this over a sibling like create_draft.

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