Draft an email

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

Annotations indicate non-read-only (mutates), non-destructive, non-idempotent. The description adds context: validates recipients, optionally links to CRM, and voiceLint behavior (scores body and attaches 'voice' as warn-only). No contradiction with 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?

Three sentences: first covers main purpose and key limitation, second adds optional CRM, third details voiceLint. Well-structured and front-loaded. The third sentence is slightly lengthy but still clear. Minimal waste.

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?

No output schema; description does not mention return value (e.g., draft ID) or how to reference the draft later. It also does not explain 'project mail center' context. Given moderate complexity (6 params) and sibling tools like 'list_mail', 'get_email', some gaps remain.

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 33% (only 'to' and 'company' described). The description mentions recipients are validated and CRM tie-in, but does not explain 'project', 'cc', 'subject', 'body' formats or constraints. For a tool with 6 parameters, this is insufficient additional guidance.

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 tool composes and saves an email draft, emphasizing it does not send. It specifies the resource ('email draft in the project mail center') and action ('compose and save'), and distinguishes from sending via explicit note. This matches 'draft_email' well.

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 description says 'does not send—there is no mail connector; the user or a future connector sends', making it clear when to use (drafting) and when not (sending). It also mentions optional CRM tie-in. However, it does not name sibling tools like 'mark_email_sent' explicitly.

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