nv_sync_inbox

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

With no annotations, the description fully discloses the asynchronous behavior: immediate return with a status object, queuing into a cloud-browser workflow that may take minutes, and the correct follow-up method. It details the semantics of pendingReason ('queued' vs 'outsideWorkingHours') and the corresponding get_workflow_result behavior, covering edge cases.

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?

Though lengthy, the description is organized into three focused paragraphs: purpose and run-once semantics, async workflow and retry warning, and pendingReason interpretation. Each sentence adds essential operational detail without redundancy.

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?

Despite lacking an output schema, the description explains the immediate return object (status, pendingReason, workflowId, operationName) and the follow-up via get_workflow_result, including edge cases like outsideWorkingHours. It is complete for a tool that initiates an async workflow, as the final result is intentionally delegated to get_workflow_result.

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 nothing to describe. The description does not need to add parameter info; the 0-parameter baseline of 4 applies, and no ambiguity exists.

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: 'Enable whole-inbox monitoring in Sales Navigator' and explains its purpose in relation to get_inbox. It also clarifies the one-time setup and temporal scope ('only messages that arrive after it is enabled are captured'), distinguishing it from related tools.

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 explicitly states 'Run once per account' and gives a key rule: 'Do not retry the original tool while a workflow is still running; that creates duplicate queued work.' It instructs to call get_workflow_result with the returned workflowId and operationName, and explains how to handle pendingReason values, including not looping on outsideWorkingHours.

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