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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds the note about returning 'lightweight draft records', which is minor extra context but does not introduce rate limits, pagination defaults, or other behavioral details.

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?

The description is two sentences, concise, and well-structured. It front-loads the core action and immediately provides a helpful pointer to the detail-oriented sibling without any filler.

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?

With a defined output schema and fully documented parameters, the description gives enough context for a simple list operation. It could mention pagination behavior or default limits, but these are not essential given the schema and the pointer to email_draft_get for details.

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% with all three parameters (limit, cursor, agentId) fully described. The description's mention of 'optional filters' aligns with the schema but adds no additional semantic detail, so baseline 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?

The description clearly states the verb 'List' and the resource 'email drafts', and explicitly distinguishes from email_draft_get by mentioning the lightweight record format and pointing to the sibling for full detail.

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 explicitly mentions using email_draft_get when full detail is needed, providing a clear alternative. However, it does not explicitly state when to avoid this tool (e.g., for creating, sending, or deleting drafts), though the sibling list implies those cases.

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