Ground Truth - Fresh Evidence for AI Agents

Endpoint Reachability Check

check_endpoint

Read-onlyIdempotent

Preflight an unfamiliar public URL or API before an AI agent relies on it. It performs one live fetch and returns a PASS/WARN/FAIL verdict with HTTP status, content type, response time, final URL/redirect behavior, auth and rate-limit signals, and a short response sample. A PASS proves only that this fetch succeeded at check time; it does not validate authenticated flows, POST side effects, JavaScript execution, or business logic.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Public http(s) URL or bare domain to probe. Bare domains like google.com are accepted and normalized to https:// automatically.

Output Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	Normalized URL that was actually fetched.
`error`	No	Validation or network error when the request could not be completed.
`status`	No	HTTP status code returned by the endpoint, when a response was received.
`summary`	Yes	Short human-readable explanation of the verdict.
`verdict`	Yes	Operational preflight verdict. It is evidence for an agent decision, not a security guarantee.
`evidence`	Yes	Structured observations used to produce the verdict.
`finalUrl`	No	Final response URL when the runtime exposes it.
`inputUrl`	No	Original user input when normalization changed it, for example when https:// was added.
`next_step`	Yes	Agent-readable follow-up for sources that should remain trustworthy over time.
`accessible`	Yes	True when the endpoint returned a 2xx HTTP status.
`redirected`	No	True when the fetch followed a redirect to a different final URL.
`contentType`	No	Response Content-Type header, if present.
`rateLimited`	No	True when the server responded with 429 Too Many Requests.
`authRequired`	No	True when the server responded with 401 or 403, which usually means credentials are required.
`responseTimeMs`	No	Elapsed request time in milliseconds.
`sampleResponse`	No	First 1,000 characters of the response body for quick inspection. Use this as a debugging hint only; it may be truncated and should not be treated as a complete page capture.
`recommended_action`	Yes	Suggested next step based only on observed response behavior.

TDQS

A4.3/5.0

Behavior5/5

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

The description is exceptionally transparent: it discloses that exactly one live fetch is performed, enumerates precisely what is returned (HTTP status, content type, response time, redirect behavior, auth signals, rate-limit signals, sample), and explicitly undermines over-trust by stating that PASS only proves fetch success at check time. This goes well beyond the readOnlyHint, idempotentHint, and destructiveHint annotations and provides critical behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and tightly structured: three sentences that front-load the purpose, list the return fields, and then state the limitations. Every sentence earns its place with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with a rich output schema, the description is fully self-contained. It covers what the tool does, when to use it, what it returns, and its limitations. There is no notable gap that would confuse an agent invoking this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully documents the single 'url' parameter, including bare-domain normalization and http(s) requirement. The tool description adds no additional parameter-specific detail beyond what the schema already provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the tool's action ('Preflight an unfamiliar public URL or API') and what it returns (a PASS/WARN/FAIL verdict with HTTP status, content type, response time, etc.). However, it does not explicitly distinguish itself from the similarly-named sibling preflight_endpoint, which likely serves the same or nearly the same purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context ('Preflight an unfamiliar public URL or API before an AI agent relies on it') and states important limitations (no validation of authenticated flows, POST side effects, JavaScript execution, or business logic). It does not explicitly name alternatives or exclusion criteria, but the context is strong enough for an agent to decide when to use it.

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

All Ground Truth - Fresh Evidence for AI Agents tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, but there are several lightly overlapping pairs (check_endpoint/preflight_endpoint, check_pricing/compare_pricing_pages, estimate_market/compare_competitors, test_hypothesis/verify_claim). The detailed descriptions and explicit 'do not use for' notes mitigate confusion, so misselection is unlikely.

Naming Consistency5/5

All tool names follow a consistent lowercase snake_case verb_noun pattern (e.g., check_endpoint, create_monitor, verify_claim). Even compound verbs like preflight_endpoint and run_monitor_now adhere to the same structure, making the naming fully predictable.

Tool Count4/5

19 tools is slightly heavy but reasonable for the broad scope covering endpoint checks, pricing, compliance, package research, claim verification, and monitor lifecycle. Each tool has a distinct role, though the count edges close to the 'heavy' range.

Completeness4/5

Core workflows are well-covered: create/list/delete/get/run/preview monitors, single and comparative pricing checks, endpoint and security verification, and claim testing. Minor gaps exist, such as no update_monitor tool or a way to explicitly verify a claim without pre-supplied evidence URLs, but these are workable.

Endpoint Reachability Check

Input Schema

Output Schema

TDQS

Glama MCP Gateway

TDQS

Resources