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

Annotations already carry readOnly/idempotent/non-destructive facts. The description adds only the 'exact' matching semantics and ID source rule, not return shape, error behavior, or auth side effects. That is acceptable but not rich, so a 3 matches the minimal added value beyond annotations.

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?

Two clauses, one sentence, no filler; the core action and the critical constraint are front-loaded. Every word contributes to correct use.

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 read-only fetch-by-ID tool, the description plus schema covers the required ID source and the account disambiguation policy via account_id. It does not describe the return payload, but the name and readOnlyHint make the outcome sufficiently predictable; a small gap remains for agents expecting error semantics.

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 100%, with the same draft_id provenance warning already present in the schema and a thorough account_id explanation in the schema. The tool description repeats the draft_id rule but adds no new parameter meaning, so it earns the schema-coverage baseline.

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 opens with 'Get one exact draft' – a specific verb and resource that make the tool's function unmistakable. It immediately differentiates from list-style siblings by emphasizing 'exact draft,' and the constraint 'draft_id must come from email_list_drafts or email_create_draft' further anchors its role in the draft workflow.

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?

It states the required ID provenance and warns against using subject/email_id, which is actionable guidance for correct invocation. It does not explicitly name alternate tools to use for other draft operations, such as email_list_drafts for searching or email_send_draft for sending, so it is not a complete routing guide.

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