gmail_account_list

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

With no annotations provided, the description takes full responsibility for surfacing behaviors. It discloses that the email may be 'cached,' notes it never returns secrets, and states it is read-only. It also names the configuration file and explains what data is exposed (including which account is default), which sets clear expectations for a low-risk, non-destructive operation.

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?

Three sentences, each with a distinct job: what it lists, how to use it, and safety/equivalence. The most important usage instruction is front-loaded in the second sentence, and the mirror command adds confidence for power users. No verbosity.

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, zero-output-schema tool, the description covers all the angles: what is listed (fields and file), how to use the output (pass to other tools), safety (no secrets), and behavior (cached email possible). Nothing an agent needs to call this correctly is omitted.

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?

This tool takes zero parameters, so per the rubric the baseline is 4. The description reinforces the 'no parameters' expectation, which adds no new info but is consistent. There is no schema to augment, so the score remains at the baseline.

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 identifies a specific action ('List Gmail accounts configured in ~/.omni-dev/settings.json') and names the exact fields returned (name, cached email, granted scope, default flag). It differentiates itself from sibling tools by framing itself as a discovery/predecessor for gmail_search, gmail_message_read, etc., which is explicitly stated.

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?

It gives an explicit when-to-use instruction: 'Call this first to discover valid `account` values before passing one to [specific tools].' It also provides an exclusion note ('Never returns a secret') and states it is read-only with no parameters. While it doesn't name direct alternatives, its role as the initial discovery step is unambiguous.

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