Submits a list of URLs to be checked and returns a job_id. Lists of up to about 200 URLs complete inline, waiting up to 60 seconds, and the results are returned directly. Larger lists return immediately with the job_id alone, and their results become available as the job progresses.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | URLs to check. Each must include http:// or https:// scheme. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description substantially enriches what annotations alone provide. It discloses exact batching behavior: up to about 200 URLs complete inline after waiting up to 60 seconds, while larger lists return immediately with only a job_id and results arrive asynchronously. This goes well beyond the readOnlyHint, openWorldHint, idempotentHint, and destructiveHint flags.
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 packs the action, return value, threshold, timeout, and async behavior into two compact sentences. It is front-loaded with the core purpose and every sentence adds information without repetition or filler.
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 tool with no output schema, the description covers the essential behavior: what is submitted, what is returned, when results are direct, and when the caller must wait for job progress. A small gap is that it could explicitly point to get_job_status for monitoring larger jobs, but that sibling tool likely carries its own 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?
Schema coverage for the single 'urls' parameter is 100%, including the requirement for http:// or https:// schemes, so the schema already carries the parameter semantics. The description adds threshold context (about 200 URLs) but does not add further meaning to the parameter itself, matching 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 states a specific action ('Submits a list of URLs'), the resource ('URLs to be checked'), and the key output ('returns a job_id'). It clearly differentiates this from the sibling get_* tools, which retrieve job results, status, usage, or domains rather than submitting work.
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 gives clear context on when inline results are returned versus when the caller should expect only a job_id, based on list size and the 60-second wait. It does not explicitly name alternatives or exclusions, but the sibling tools are complements rather than competing submit endpoints, so the lack of an explicit when-not is a minor gap.
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.
