Audit websites for AI search readiness and check whether a business shows up in AI answers (ChatGPT, Perplexity, Google AI Overviews). API key auth, free account at qleerly.ai.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 2 tools
audit_site and check_ai_visibility have clearly distinct purposes: one performs a technical/structural audit of the page, the other runs a live search simulation to test discoverability. The description explicitly orders them ('use this first, before check_ai_visibility'), leaving no room for misselection.
Both names follow the same snake_case verb_noun pattern (audit_site, check_ai_visibility) and use precise, descriptive verbs. No stylistic deviation.
Two tools is thin for a product centered on AI-search visibility; the natural workflow (audit -> diagnose -> fix -> re-check) is only partially exposed. It is defensible as a minimal MVP surface, but agents will quickly run out of actions.
The two tools cover diagnosis and verification of AI visibility, but there is no remediation step (e.g. applying structured-data or metadata fixes) and no historical/trend reporting despite the tool mentioning scores. An agent can diagnose but cannot act on findings, creating a dead end.
Checks whether a public website can be read and understood by AI answer engines (ChatGPT, Perplexity, Google AI Overviews): crawler access, structured data, headings, metadata and other signals. Returns a score and concrete findings. Use this first, before check_ai_visibility, to see what is technically blocking AI search.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Full public URL, e.g. https://example.com/ |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses the return content ('score and concrete findings') and implies a read-only external fetch via 'checks','audit', but does not cover latency, rate limits, behavior on unreachable/non-public URLs, or whether the crawl is live. Adequate but incomplete for a zero-annotation 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?
Three sentences, front-loaded with what is checked, then the output, then the routing instruction. Every sentence carries distinct information with no 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?
With no output schema, the description correctly explains what is returned (score plus findings) and scopes the tool to public sites. It omits failure modes for inaccessible sites, which is a minor gap for a simple one-parameter auditing 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?
Schema coverage is 100% with a single well-documented 'url' parameter (format uri, example given), so the schema already does the work. The description adds no format or constraint detail beyond it; 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 ('checks') and resource ('public website'), enumerates exactly what is inspected (crawler access, structured data, headings, metadata), and explicitly distinguishes itself from check_ai_visibility. An agent knows precisely what this tool does 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?
Explicitly says 'Use this first, before check_ai_visibility' and gives the reason (to see what is technically blocking AI search). This is a named alternative plus the condition that selects it — nothing left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Runs a real web search the way an AI answer engine would, and reports honestly whether the business behind the URL is found or recommended, and which real competitors show up instead. A negative result is a valid result. Requires the Qleerly Plus plan or higher.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Full public URL of the business website |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does add real value: it discloses the Qleerly Plus plan requirement and frames the negative outcome as a legitimate result, which shapes how an agent interprets the response. Gaps remain (latency, cost, whether it is purely read-only), but the disclosure is meaningfully richer than typical.
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?
Three tight sentences with the action front-loaded, followed by interpretation guidance and the entitlement requirement. No 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 single-URL check tool with no output schema and no annotations, the description covers the what, the interpretation stance, and the plan requirement. It is nearly complete; only result-shape and sibling differentiation are absent.
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?
Only one parameter (url) at 100% schema coverage, so the schema already documents it fully. The description adds only the framing of 'the business behind the URL,' which is marginal, 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?
States a concrete verb and resource: runs a web search the way an AI answer engine would and reports whether the business is found/recommended. Clear and specific, but it never names the sibling audit_site, so the agent must infer the boundary between the two.
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?
Usage is implied ('runs a real web search... reports whether the business is found or recommended') and it usefully clarifies that a negative result is valid. However, no explicit when-to-use condition or alternative to audit_site is given.
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.
audit_sitecheck_ai_visibility
Add one secure layer between your agents and this server.