draft

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

Annotations already declare the non-read-only, non-destructive, non-open-world profile, and the description adds substantial context beyond them: drafts are silently NOT saved when suspect files or HEIC photos are involved, programs are always refused, signatures are auto-appended, attachments are capped at 2 MB each, and delete moves to Trash. This is unusually rich behavioral disclosure for a mutation tool.

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?

It is long, but 22 parameters with three attachment channels and three sub-modes genuinely justify the length, and the safety-critical 'NOTHING IS SENT' constraint is front-loaded. Bullets are organized by task rather than alphabetically, though a few lines restate schema text almost verbatim.

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?

An output schema exists, so return-value explanation is unnecessary, and every behavioral branch an agent needs – delete, mode='signatures'/'files', attachment sourcing, signature handling, HEIC and suspect-file refusals – is covered. Nothing required to call this 22-parameter tool correctly is missing.

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 adds real value the schema does not: it groups parameters into the New-email flow (to/subject/body), explains the reply_to vs reply_all vs forward ID semantics, and notes that omitted fields on edit stay unchanged. It stops short of documenting cc/bcc alongside the flow, so it is good rather than exhaustive.

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?

Opens with a specific verb+resource ('Create or edit a draft in a Drafts folder') and immediately differentiates the tool from its closest sibling by stating 'NOTHING IS SENT (use send_email for that).' An agent can tell this apart from send_email and schedule_send without opening 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?

Explicitly routes to alternatives ('use send_email for that') and gives conditional rules for nearly every path: delete must be the only argument, photos='smaller' only when asked or after agreement, HEIC drafts require first asking the user, allow_suspect only after telling the user the reasons. When-to-use and when-not-to-use are both spelled out.

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