nv_manage_conversation

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

With no annotations, the description fully discloses the async queued workflow: it 'may take several minutes', returns immediately with a status object, and long-polls via get_workflow_result. It explains the pendingReason values 'queued' and 'outsideWorkingHours' and gives explicit instructions for each case, including not looping on outsideWorkingHours. This is exemplary transparency for a mutation 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 structured into three paragraphs, each carrying distinct information: core action, async response and retrieval pattern, and pending-state handling. It is longer than average but the complexity of the workflow justifies the length; every sentence adds operational value. It could be slightly tightened by merging repeated mentions of get_workflow_result, but it remains well-organized.

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?

The tool has no output schema, and the description compensates by explaining both the immediate return object and the eventual result retrieval via get_workflow_result. It covers the async execution model, retry avoidance, and edge cases like outsideWorkingHours. For a tool with this complexity, the description is comprehensive and leaves no critical operational gap.

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?

Both parameters are fully described in the schema (100% coverage), so the baseline is 3. The description reiterates the threadId source and operation, but adds no additional format constraints, examples, or edge-case semantics beyond what the schema already provides. Therefore it does not elevate above 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 opens with 'Archive or unarchive a Sales Navigator conversation thread by threadId' — a clear action (archive/unarchive) applied to a specific resource (Sales Navigator conversation thread) with the key input identified. This distinguishes it from related tools like retrieve_feed or search, and the mention of 'nv.manageConversation action' ties it to a specific API operation.

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 explicitly states that the threadId should come from get_inbox and instructs the caller to retrieve the final result via get_workflow_result with the returned workflowId and operationName. It provides explicit guidance on when not to retry ('Do not retry the original tool while a workflow is still running') and how to handle queued vs outsideWorkingHours states. This gives robust operational context, though it does not contrast with the non-nv manage_conversation sibling.

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