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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false. The description adds important behavioral context beyond those annotations: it returns an id, never transmits, has a per-message external recipient cap of 10, and the draft is owned by the connected user rather than the agent.

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 front-loaded with the core purpose and then adds only relevant constraints: draft-only behavior, optional recipients, recipient cap, and ownership. Every sentence adds useful information, and there is no wasted text.

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?

Given the annotations and lack of an output schema, the description covers essential call behavior: purpose, draft-only semantics, return id, recipient optionality, and ownership. It remains slightly incomplete because it does not explain bodyContentType or clarify cc/bcc semantics, though the schema partly covers required fields.

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 low at 17%, with only the 'to' parameter documented in the schema. The description adds that recipients are optional and mentions an external recipient cap, but does not explain cc/bcc distinction, subject/body requirements, or bodyContentType's text/html enum, leaving much parameter meaning undocumented.

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 a specific verb and resource: create a draft email in the authorized user's Outlook mailbox. It also corrects the potentially misleading tool name by clarifying 'Draft-only ... it never transmits.' However, it does not explicitly distinguish this tool from sibling compose or messaging tools.

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 usage by stating the draft is for the user to review and send themselves from Outlook, and that it never transmits. It does not name alternatives or give explicit when-not-to-use guidance. Usage is inferable but not fully specified.

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