gmail_compose_state

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

With no annotations, the description carries the full burden. "Describe" implies a non-mutating read and the field list tells the agent what comes back, which is valuable. It does not disclose failure behavior when no compose window exists or whether the call has any side effects, so gaps remain.

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?

A single sentence, front-loaded with the verb and the target, with the parenthetical list doing useful work. Nothing is redundant or padded.

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 zero-parameter, no-output-schema state-read tool, the description covers the important ground by listing the returned fields and the precondition that a compose window be open. Only the error/empty-state behavior is left unaddressed.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The field enumeration adds context about what state is surfaced but is not a parameter concern.

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?

Specific verb ("Describe") plus a specific resource ("the compose window currently open"), and it enumerates exactly what is reported: mode, recipients, subject, body, attachments. It is clear what the tool does, but it never names how it relates to siblings like gmail_draft or gmail_edit_draft, which also touch compose state.

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?

"Currently open" implicitly tells the agent a compose window must exist first, which is a useful precondition. However, there is no explicit when-to-use guidance, no statement of what to do if no compose window is open, and no reference to an alternative tool for reading a saved draft instead.

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