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

Annotations only say readOnlyHint and openWorldHint; the description goes far beyond them by disclosing the asynchronous cloud-browser workflow, the immediate {status, pendingReason, workflowId, operationName, message} return shape, multi-minute latency, and duplicate-queue risk. The pendingReason semantics ('queued' vs 'outsideWorkingHours') and the instruction to report the window opening to the user rather than loop are exactly the kind of behavior an agent cannot infer elsewhere.

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?

Purpose is front-loaded and the paragraphing separates purpose, workflow mechanics, and pendingReason states. However the get_workflow_result hand-off is stated twice (once as an aside after "Plus required" and again as a full instruction), and the "Plus required" fragment is unexplained noise that sits inside the purpose sentence.

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 one-parameter, no-output-schema async tool the description covers the full lifecycle: immediate acknowledgement, polling contract, pending reasons, and terminal outcomes. The only real gap is that the eventual saved-search payload shape is never characterized, and "Plus required" leaves an unresolved requirement (plan tier or scope) ambiguous.

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 description coverage is 100% and the single enum parameter is fully documented in the schema, so the description needs only to be consistent — which it is via "of the requested type." It adds no syntax or meaning beyond the schema, but with one fully-described enum parameter there is little left to add, putting it slightly above the flat 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 a specific verb+resource ("Retrieve owned saved searches of the requested type") and the schema enum narrows it to lead/account subject types, so an agent can distinguish it from nv_create_saved_search or nv_delete_saved_search. It never names its closest read siblings (nv_retrieve_lists, nv_retrieve_alerts), so differentiation is inferred rather than stated.

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 routes follow-up to get_workflow_result with operationName nvRetrieveSavedSearches and states a hard exclusion: "Do not retry the original tool while a workflow is still running; that creates duplicate queued work." That is a genuine when/when-not rule with a named alternative, though there is no guidance on when to prefer saved searches over lists or alerts.

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