gmail_label_list

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

Even without any annotations, the description carries the full behavioral burden and does it well: it flags the operation as read-only, states the output format (YAML), lists the returned data fields, and notes the CLI equivalent. The one-sentence zhurnada about the mutation boundary is a useful context signal for an agent reasoning about the tool family's capabilities. It could go further by describing the exact YAML shape or auth-side effects, but for a small read-only listing tool, this is thorough.

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?

Every sentence carries weight: the scope, the data returned, the mutation boundary, the CLI mirror, the output format, and read-only status are each covered without repetition. The mutation-boundary sentence, though about the broader family, earns its place by setting agent expectations. A very brief output-format sentence feels slightly terse but is perfectly functional.

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 tool with this complexity (1 optional arg, no required parameters, shallow return data), the description is nearly complete. It covers output format, data included, and even names the sibling for account discovery. Minor omissions like the exact YAML shape or behavior on an empty label list are forgivable at this low complexity.

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 optional `account` parameter is already well-documented with defaults, resolution semantics, and a pointer to gmail_account_list. The description doesn't add explicit param-level info, but at this schema coverage level the burden is already met. The baseline of 3 applies.

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 opens with a specific verb and resource ('List every label on the Gmail mailbox'), enumerates what counts as a label (system + user-created), and specifies exactly what the output contains (unread/total counts). Across the Gmail sibling family (gmail_search, gmail_message_read, gmail_account_list), this tool is unambiguous in scope.

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 states what the tool covers and explicitly draws the line at mutation ('Adding or removing labels on messages is CLI-only in this release'), so an agent won't expect mutation ability here. The schema goes further by naming gmail_account_list for discovering account names, and the description offers the CLI mirror as a reference. It never explicitly says 'use X instead of this' for the core listing behavior, so it stops just short of a perfect score.

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