sync_inbox

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

With no annotations provided, the description takes full responsibility for behavioral disclosure. It thoroughly explains the asynchronous nature: the server returns immediately with a status object, the action is queued into a cloud-browser workflow, and get_workflow_result must be polled. It also details pendingReason meanings ('queued' vs 'outsideWorkingHours') and instructs on the correct action for each, including not looping when outside working hours. This exceeds what annotations would typically provide.

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 well-structured and front-loaded with the core purpose, then dives into the async workflow and edge cases. It is thorough but not verbose — every sentence adds actionable information (e.g., status fields, pendingReason handling, the prohibition on retries). The three-paragraph format is easy to scan and each paragraph covers a distinct aspect: purpose, async workflow, and pending-state semantics.

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?

Given the complexity of the async workflow and the lack of an output schema, the description is remarkably complete. It explains the immediate return value, how to retrieve the final result via get_workflow_result, the long-poll behavior, and both pendingReason cases with explicit instructions for the agent. It even covers the 'request budget' aspect, making the description sufficient for an agent to handle the entire lifecycle without further documentation.

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 input schema has zero parameters, so there is no parameter-specific semantics to add. The description focuses on the tool's operation and return values instead. Per the rubric, a baseline of 4 is appropriate for 0 parameters; the description adds meaning by explaining the output and workflow behavior, which is the next best thing.

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 the tool's purpose: 'Enable whole-inbox monitoring so every incoming conversation can be polled with get_inbox'. It uses a specific verb ('Enable') and resource ('whole-inbox monitoring'), and distinguishes it from the related get_inbox tool by explaining the enablement prerequisite. It also clarifies the scope ('Run once per account') and a key behavioral constraint ('only messages that arrive after it is enabled are captured').

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 clear usage context: it must be run once per account before get_inbox can poll, and it explicitly warns against retrying the tool while a workflow is running ('Do not retry the original tool while a workflow is still running') to avoid duplicate work. It does not directly compare to sibling alternatives, but the one-time setup instruction and workflow handling guidance effectively tell the agent when to use it and how to proceed after invocation.

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