Save draft

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

Annotations only declare the safety profile (not read-only, not destructive, not open-world); the description adds genuinely non-obvious behavior — attachments are actually uploaded to the mail server, so the draft carries real side effects and needs approval first. It does not say whether an existing draft is overwritten, what is returned, or how reply_to_uid affects threading.

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 sentences, zero waste: the core action and its key distinction come first, and the attachment-approval caution follows. Every sentence earns its place.

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 9-parameter mutation tool with no output schema, the description covers the riskiest behavior (server-side attachment upload) and the approval gate. Minor gap: the presence of reply_folder/reply_to_uid means this can create a reply draft, which the description never mentions.

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%, including the detailed attachments constraint referencing list_attachment_folders, so the schema already carries parameter semantics. The description only reiterates the attachment approval need and adds nothing about account, reply_folder, or reply_to_uid beyond what is documented.

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?

States a specific verb and resource (save a message to the Drafts folder) and immediately carves out the boundary versus send_email with 'without sending it'. An agent can distinguish this from send_email or save_attachments without inspecting any schema.

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?

Clear context for when to use it (draft instead of send) and an explicit pre-condition workflow for the attachment case: show file paths and get user approval. It stops short of naming send_email as the alternative path or saying when a draft is preferred over sending.

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