get_visibility_checkCollect the result of a measurement started with start_visibility_check. Returns status running while the providers are still answering, so poll every 20 to 30 seconds. When ready it reports a verdict, how many of the buyer questions the brand won, which competitors were named instead, and which providers actually answered.
| Name | Required | Description | Default |
|---|---|---|---|
| runId | Yes | From start_visibility_check |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond those annotations: the 'running' status, recommended polling interval, and the specific result payload (verdict, questions won, competitors named, providers answered). This helps the agent know what to expect and how to interact without over-explaining.
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?
Two efficient sentences deliver the core action, the polling behavior, and the result contents with no filler. The purpose is front-loaded, and every clause adds useful information for correct invocation.
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 one parameter, annotations covering safety, and no output schema, so the description carries the burden of explaining return values. It does so by naming the status condition and the specific types of data returned. It could be slightly more explicit about the response shape, but for a single-parameter polling tool this is sufficient.
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 schema description already covers the only parameter fully ('From start_visibility_check'), so the description does not need to add much. It reinforces the relationship by saying the measurement was started with start_visibility_check, but otherwise adds no new parameter-level meaning. This matches the baseline for high schema coverage.
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 a specific verb ('Collect the result') and resource ('measurement started with start_visibility_check'), and the sibling relationship is evident: this tool retrieves results, while start_visibility_check initiates the measurement. The scope is unambiguous and an agent can distinguish it from its only sibling without opening the schema.
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 implicitly but clearly tells the agent when to use it: after start_visibility_check has been called. It also provides concrete polling guidance ('poll every 20 to 30 seconds') while the measurement is running. It does not explicitly state exclusion cases or mention start_visibility_check as the alternative, but the prerequisite and context are unmistakable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The two tools have clearly distinct roles: start_visibility_check initiates an asynchronous measurement, while get_visibility_check retrieves its result. There is no overlap in purpose, and the start/get contrast makes the workflow obvious.
Both tools follow the same verb_noun pattern using the shared resource 'visibility_check' with prefixes start_ and get_. This creates a predictable and consistent naming convention.
Two tools is minimal and slightly below the typical 3-15 range, but each tool is necessary for the single async measurement workflow. The count feels appropriate for the narrow, focused purpose of the server rather than bloated.
The server covers the full lifecycle of its core domain: starting a visibility measurement and retrieving its outcome. There are no obvious dead ends, since start returns a runId and get returns both in-progress and final states.