create-draft-email

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

Annotations declare readOnlyHint=false, so the write nature is already known. The description adds genuine behavioral context beyond that: the draft is persisted to the Drafts folder and is NOT sent, which materially affects how an agent sequences this call. Given annotations already carry the safety profile, this is solid added value without contradicting anything.

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 tightly packed sentences: purpose and location first, then settable fields, then the critical save-vs-send disambiguation. No filler or redundancy; every sentence earns its place. Could perhaps front-load the 'not sent' clarification even earlier, but the structure is efficient.

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 draft-creation tool with annotations covering the write/destructive profile, the description captures the essential behavior: it saves a draft, names the settable fields, and disambiguates from sending. Optional fields like attachments and bcc are absent but are documented in the schema body nested properties. The confirm-gate parameter is self-documented in the schema, so no gap there. An agent can call this correctly with the given information.

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 75% (moderately high), so the schema documents most parameters. The description names the key message fields (subject, body, toRecipients, ccRecipients, importance) which maps to nested schema properties and adds modest orientation for an agent. It does not add format or syntax details beyond the schema, so a 3 baseline is appropriate.

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 uses a specific verb+resource+scope: 'Create a draft Outlook email message in the signed-in user's Drafts folder.' It names the settable fields (subject, body, toRecipients, ccRecipients, importance) and explicitly contrasts itself with send-mail by stating the draft is saved, not sent. An agent can immediately tell what this tool does and how it differs from send-mail/send-draft-message.

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 gives clear when-to-use context: it states the draft is not sent and points to send-mail as the alternative for direct sending ('use send-mail to send a message directly, or send the draft afterwards'). However, among the large sibling set there are create-forward-draft, create-reply-draft, and create-reply-all-draft, which are not explicitly excluded; the phrase 'draft Outlook email message' only indirectly implies a fresh draft. Some exclusion guidance for those variants would push this to 5.

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