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

Annotations only declare openWorldHint/idempotentHint=false/destructiveHint=false; the description adds far more — delivery is immediate and irrevocable, the CURRENT subject/body (not a snapshot) is what is sent, and precise 409/422 failure semantics are enumerated. This is exactly the extra behavioral context annotations cannot convey.

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?

Front-loaded with the core action and its irreversibility, then prerequisites and error codes. Three dense sentences, each carrying load, though the error-code enumeration makes it slightly heavy for a single-parameter tool.

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 one-parameter mutation with no output schema, it covers the action, the irreversibility, the required pre-read/draft-fix workflow, the sibling tools to use, and both refusal modes — nothing an agent needs to invoke it correctly is missing.

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% and the single 'id' parameter already documents itself as the numeric reply draft ID. The description only reinforces the provenance ('from list_reply_drafts') without adding format or validation detail beyond the schema, so the baseline of 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+resource+mechanism: sends an AI reply draft through the conversation's sender mailbox, scheduled immediately. It is clearly distinguishable from siblings like update_reply_draft or list_reply_drafts, which it explicitly names.

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 an explicit pre-flight workflow ('read it first via list_reply_drafts or get_lead_conversation and fix it with update_reply_draft if needed') and names the exact refusal conditions (409 for non-sendable drafts, 422 for missing sender mailbox or recipient). When-to-use and when-it-will-fail are both spelled out.

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