draft_email

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

No annotations are provided, so the description carries full burden of behavioral disclosure. It mentions 'matching your writing style from previous emails' which is a useful behavioral trait, but it doesn't state that create_draft defaults to false (so by default no draft is saved), what happens with the generated text (is it returned for preview? auto-sent?), or the AI-negotiation aspects. The description implies AI generation but is vague on side effects.

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 compact at two short paragraphs, front-loaded with the core purpose. Every sentence contributes. It could be slightly tighter, but it's efficient and readable without padding.

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?

There is an output schema which offloads return-value documentation, and 100% schema coverage handles parameters. However, for an AI-assisted draft tool, the description doesn't clarify the default no-draft behavior (create_draft=false), how the user interacts with the AI-generated output, or typical invocation patterns. It's adequate but not thorough for a generative tool with multiple siblings in the same domain.

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%, so schema already documents all 6 parameters. The description adds the 'matching your writing style' context and clarifies the intended workflow, but doesn't add syntactic or semantic depth beyond what the schema provides. Baseline 3 is appropriate given the full schema coverage.

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 'Draft a new email with AI assistance' with a specific verb+resource and mentions it creates drafts based on context/instructions, matching writing style. It's clear about the core function but doesn't distinguish from siblings like draft_reply or draft_follow_up, which have similar drafting purposes — though the name itself plus context clarifies new email vs reply/follow-up.

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 implies when to use it (creating a new email draft) but doesn't explicitly exclude alternatives like draft_reply or draft_follow_up, nor does it explain the relationship to send_email vs create_email_draft. The context makes the use case reasonably clear, but no explicit when/when-not guidance or named alternatives are provided.

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