Open a compose window

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

The description adds context beyond annotations: it reveals that the tool opens a UI window, does not send or save, and is not gated. Given annotations only show readOnlyHint=false, etc., the description meaningfully informs behavior without contradicting annotations.

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 relatively concise at 4 sentences, front-loading key info. However, some phrasing like 'the right answer whenever...' is slightly verbose, and 'so this is not gated' may not be universally clear.

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?

Despite having 12 parameters and no parameter descriptions in the tool description, the description fails to explain parameter usage. The output schema exists but isn't referenced. Completeness is low for a tool with this many parameters.

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 0%, and the tool description provides NO information about any of the 12 parameters (to, cc, subject, etc.). It only says 'populated compose window' without explaining what each parameter does. This is a critical gap.

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 clearly states it opens a populated compose window for manual finishing, distinguishing it from send/save tools. It explicitly says 'nothing is sent or saved' and 'user sees window appear', differentiating it from siblings like mail_send and mail_draft_save.

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 provides explicit guidance on when to use: 'when the wording matters more than the automation, or when the user declined a send'. It also clarifies what the tool does not do: 'nothing is sent or saved' and that it is 'not gated'.

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