Read a saved draft

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false. The description adds useful behavioral context beyond that: exactly one reference must be passed, protected or oversized drafts return metadata with editable=false, and a preview must not be used as a replacement body.

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 no wasted language. The purpose is front-loaded, and the parameter rule and behavioral caveats follow in a logical order.

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 and annotations cover the safety profile, so the description need not explain return values. It covers the saved-snapshot scope and key edge cases, though it remains incomplete on parameter identification for a tool with two undocumented parameters.

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%, so the description must compensate. It adds an important constraint ('Pass exactly one reference') that is not expressed in the schema, but it does not explain what draft_ref versus message_id mean or their formats, leaving a clear gap.

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?

The description states a specific verb and resource: reading a saved draft and its revision, explicitly without opening a composer. This distinguishes it from generic mail retrieval and from composer-oriented siblings such as mail_compose_open.

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 phrasing 'without opening a composer' and the note that unsaved changes in an open Thunderbird window are not this saved snapshot imply when to use it rather than a live composer. However, it does not explicitly name alternatives or when-not conditions for siblings such as mail_get or mail_draft_update.

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