Scan a public homepage for cookies and tracking observed before consent interaction.
Scored across 2 tools
The two tools form a clean create/read pair: start_quickscan initiates a scan and get_quickscan_result polls it by scanId. The descriptions explicitly cross-reference each other, so an agent can't mistake one for the other.
Both names use consistent snake_case with a verb_noun structure (start_quickscan, get_quickscan_result) and share the same domain noun. Params like scanId, pollAfterSeconds, and retryAfter follow a uniform camelCase convention.
Two tools is thin even for a narrow 'quickscan' purpose, but the async start-then-poll pattern genuinely requires exactly this pair. It sits at the borderline rather than being mismatched.
Create plus retrieve covers the full scan lifecycle for this narrowly scoped domain, and out-of-scope items (accept/reject, legal verdicts, bulk) are declared. Minor gaps remain: no cancel/abort for an in-flight scan and no way to list or revisit prior scanIds.
Use the scanId returned by start_quickscan to retrieve progress or sanitized findings, including the visible banner provider and controls, CookieRisk score, pre-consent tracking status, tag or service classifications, browser-recorded initiator hosts and consent signals when available. Page settings and scan-wide network signals are separate. A request in a tracking category alone is not confirmation. Observe pollAfterSeconds before polling and retryAfter on an error. Unknown, incomplete and failed scans do not establish absence of tracking. Accept and reject behavior is outside the scan scope.
| Name | Required | Description | Default |
|---|---|---|---|
| scanId | Yes | The scanId returned by start_quickscan. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, but the description adds substantial behavior beyond them: polling cadence via pollAfterSeconds, error backoff via retryAfter, handling of unknown/incomplete/failed scan states, and an explicit caveat against interpreting categories as confirmed tracking. It also bounds scope by excluding page settings, scan-wide network signals, and accept/reject behavior.
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 purpose and returned data are front-loaded, followed by caveats and polling mechanics. Every sentence carries information, though the caveat block is dense and could be tightened into fewer clauses without losing meaning.
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?
With no output schema, the description takes on the burden of explaining what comes back and does so field by field. It also covers async polling behavior, error retry signals, and the interpretive limits of partial or failed scans, which is everything an agent needs to call and read this correctly.
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?
There is a single parameter at 100% schema description coverage, and the description's reference to 'the scanId returned by start_quickscan' merely restates the schema text. No additional syntax, format, or edge-case meaning is added beyond the schema, so the baseline of 3 applies.
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?
Uses a specific verb ('retrieve') plus the exact returned payload: progress or sanitized findings, banner provider and controls, CookieRisk score, pre-consent tracking status, classifications, initiator hosts and consent signals. It also delineates scope by noting page settings and scan-wide network signals live elsewhere, which lets an agent distinguish this read from its sibling start_quickscan. The only shortfall is that the sibling relationship is framed purely as a producer/consumer link rather than an explicit alternative.
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?
Clearly states to use the scanId from start_quickscan, and gives concrete operational instructions: observe pollAfterSeconds before polling and retryAfter on an error. It also states what the result does NOT prove (a tracking category alone is not confirmation; unknown/incomplete/failed scans don't establish absence) and that accept/reject behavior is out of scope. No explicit when-not-to-call-this-tool statement beyond those scope exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use this when a user asks to check a public website homepage for cookies and tracking observed before interaction. Creates a scan and visits the website. Only submit the homepage URL; do not use for private pages, legal verdicts, accept/reject testing, monitoring, or bulk scans. If reused is true, tell the user right away when the evidence was recorded (evidenceCapturedAt, if known) and when the domain cooldown ends (domainCooldownEndsAt). A new scan still depends on capacity. Poll get_quickscan_result using the returned scanId and wait pollAfterSeconds between reads.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public HTTP(S) homepage, for example https://example.com/; no path, query, credentials or fragment. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare the generic profile (not read-only, open-world, not idempotent, non-destructive). The description adds substantive behavior beyond that: the scan triggers an actual site visit, submission depends on capacity, reuse produces prior evidence with evidenceCapturedAt and a domainCooldownEndsAt window, and the caller must poll rather than wait for an inline result.
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 and exclusions are front-loaded, and the polling instructions come last in the natural reading order. The reuse/cooldown sentence is dense with three field names in a row, slightly taxing, but every sentence carries operational information an agent needs.
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?
With no output schema, the description carries the return-value burden and does so partially: it names scanId, pollAfterSeconds, reused, evidenceCapturedAt, and domainCooldownEndsAt, and explains the polling protocol. What is missing is what the eventual result contains or how to handle a capacity rejection, leaving a small but real gap for a scan tool.
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?
There is a single parameter at 100% schema coverage, and the schema description already spells out the URL format restrictions (no path, query, credentials, fragment). The description reinforces 'Only submit the homepage URL' and adds 'public', but contributes no syntax or format detail the schema lacks, so the baseline 3 applies.
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?
States a specific verb and resource ('Creates a scan and visits the website') with the exact scope ('public website homepage for cookies and tracking observed before interaction'). It also names the sibling get_quickscan_result as the follow-up, so an agent can distinguish the two without opening either 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?
Explicit when-to-use ('user asks to check a public website homepage... before interaction') plus a concrete exclusion list: private pages, legal verdicts, accept/reject testing, monitoring, bulk scans. It also routes the agent to the next step via get_quickscan_result, which is the strongest form of alternative-routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_quickscan_resultstart_quickscanCheck what a site's cookie banner really blocks: CMP, trackers, cookies before consent.
Cookie consent scanner: GDPR, CCPA, GCMv2. PASS/FAIL compliance checklists with fix recommendations.
Check if your website or Android app tracks visitors before cookie consent; catch broken analytics.
Inspect authorized website tracking, compare consent observations, and get remediation guidance.
Add one secure layer between your agents and this server.
