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

Adds real context beyond the annotations: nothing is sent, a card is rendered in chat with recipients/subject/body, 'Open in Gmail' pre-fills a reviewable draft, and it works with or without a connected mailbox. It does not reconcile the destructiveHint=true annotation (e.g. whether an existing draft can be overwritten or whether drafts persist in the mailbox), so one behavioral gap remains.

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?

Front-loaded with the action and the safety fact ('Nothing is sent'), then the UI consequence, then the formatting rules, then the routing rule. It is on the long side and the formatting sentence is dense, but nearly every clause carries operational value.

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 no output schema, and the description compensates by describing the returned artifact (chat card with recipients, subject and body) and the 'Open in Gmail' affordance. Combined with the mailbox-optional note and formatting instructions, an agent has everything needed to call it correctly.

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 100%, so the baseline is 3, but the description earns an extra point by specifying the expected body format (plain text, short paragraphs separated by blank lines, '- ' lists, no markdown emphasis or headings) and the tone ('user's voice'), which directly shapes the body parameter. It says nothing extra about account or cc, so not a 5.

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 ('Draft an email in Gmail') and immediately scopes it with a concrete example and the reassurance that nothing is sent. It also distinguishes itself from the nearby-looking siblings create_outlook_draft and draft_email_in_gmail by naming Gmail explicitly and contrasting with send_email.

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?

Gives an explicit routing rule: 'Use this whenever the user wants an email written to someone else; send_email remains only for mailing the user their own address.' That is a when-to-use plus a named alternative with the condition that selects it, leaving little to inference.

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