Draft a reply to a message

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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description adds the key non-obvious facts: the draft is written to a dedicated folder and is NOT sent. It also discloses the return payload (draft_id, SHA-256 fingerprint, full text). It doesn't state idempotency or overwrite behavior for repeated calls, which is the remaining gap.

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 tightly packed sentences, front-loaded with the action and destination, then the id trap, then the return values, then the safety/workflow instruction. No filler and no repetition of schema or annotation content.

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?

An output schema exists so return values needn't be explained, yet the description still summarizes them usefully. It covers the safety posture and the review workflow completely, but omits how default recipients are derived for a reply-all and what replace_recipients/exclude do, which an agent needs to call it correctly.

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 0% across 8 parameters, so the description carries the full burden. It compensates well for the critical message_id (RFC Message-ID format, example, and explicitly not the mail_search numeric id) but leaves cc, bcc, exclude, attachments, and replace_recipients entirely unexplained, including the two least self-evident ones.

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 (generate), a precise artifact (RFC5322 reply-all draft), and the destination (MCP-dedicated draft folder). It is immediately distinguishable from mail_send and mail_show, and even clarifies the reply-all scope that the name implies.

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?

Explicitly routes the agent: message_id comes from mail_show (not the numeric id from mail_search), and the tool is a pre-send step whose output must be reviewed conversationally before calling mail_send. It names both the source tool and the follow-up tool with their selection conditions.

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