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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=false, so the description does not need to restate that this mutates state. It still adds genuinely useful behavior: "This never sends" bounds the blast radius of a destructive tool, the version-gated replacement is consistent with the non-idempotent hint, and the mandatory user review is a workflow fact an agent cannot infer from structured fields.

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 with zero filler, and the two highest-value facts — the version-gated replacement and the never-sends guarantee — are front-loaded. Nothing repeats structured data.

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 destructive mutation with 5 required parameters and no output schema, the description covers the essentials: it replaces rather than creates, it is version-gated, and it cannot send. Minor gaps remain, such as what happens on a version mismatch or whether omitted optional fields are cleared, but the core call decisions are supported.

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 only 40% across 10 parameters, so the description is expected to compensate, and it only does so for the version token ("at its current version" clarifies version as a currency check, not an arbitrary integer). It says nothing about draftId, to, cc, subject, or senderIdentityId, though html/text/timeZone/scheduledAt are documented in the schema itself.

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?

"Replace a pending draft at its current version" gives a specific verb (replace) and resource (pending draft) plus the concurrency constraint that a version is involved, which separates it from creation-oriented siblings like prepare_draft or create_mailbox_draft. It stops short of naming those siblings explicitly, so the differentiation is implied rather than stated.

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 phrase "pending draft" and "at its current version" imply this is for editing an already-existing draft the user can see, and "Every edit requires the user to review the new version" signals the review-loop workflow. However, no alternative is named and no when-not condition is given (e.g. what to do if the draft is already sent/scheduled, or whether to use update_mailbox_draft instead).

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