bulk_action

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals batch processing in groups of 1000, that a query affects every match, that trash is recoverable for 30 days, and that an empty selection is refused to prevent sweeping the whole mailbox. These are critical safety behaviors an agent needs before invoking the 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?

The description is three dense sentences with no filler. It front-loads the purpose, then covers selection semantics, action verbs, safety behavior, and a preflight tip. Every sentence earns its place.

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 5-parameter mutation tool with no output schema, the description covers what matters: selection, scale, safety, action semantics, and a related tool for preflight checks. It does not explain return values, but since there is no output schema, that is not required. The description is complete enough for an agent to invoke this tool correctly.

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?

Although the input schema already documents all five parameters (100% coverage), the description adds meaning the schema lacks: the three mutually exclusive selection modes (one id, list of ids, or query) and how they behave. It also clarifies the action enum as a friendly verb layer, making the parameters more actionable than the schema alone.

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: 'Apply a named action to a SELECTION of messages in one call.' It lists the exact action verbs and explicitly positions itself as a 'friendly verb layer over modify_labels,' which clearly distinguishes it from the sibling modify_labels tool.

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 strong guidance: selection can be a single id, list, or query; query acts on every match; and it recommends running count_messages first to assess blast radius. It names modify_labels as the label-based alternative, but it does not explicitly state when not to use bulk_action or when to prefer sibling tools like trash for single-message operations.

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