Ground Truth - Fresh Evidence for AI Agents

Endpoint Preflight

preflight_endpoint

Read-onlyIdempotent

Run reachability/response and security-header checks together for an unfamiliar URL or API before an AI agent trusts or acts on it. Returns one combined PASS/WARN/FAIL verdict with evidence from both checks. It does not prove that a service is safe, authenticated, or correct.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "preflight_endpoint"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Public http(s) URL or bare domain to preflight.

Output Schema

Name	Required	Description
`url`	Yes	Normalized URL that was checked.
`summary`	Yes	Short explanation of the combined verdict.
`verdict`	Yes	Combined preflight verdict.
`evidence`	Yes	Evidence from the endpoint and security-header checks.
`next_step`	Yes	Concrete follow-up after reviewing the evidence.
`recommended_action`	Yes	Suggested next step.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedAug 7, 2026

addedOutput schema / properties / next_step

Added value: +{
+  "description": "Concrete follow-up after reviewing the evidence.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "url",
-  "verdict",
-  "summary",
-  "evidence",
-  "recommended_action"
-]New value: +[
+  "url",
+  "verdict",
+  "summary",
+  "evidence",
+  "recommended_action",
+  "next_step"
+]

AddedAug 5, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds behavioral details about the return value (one combined PASS/WARN/FAIL verdict with evidence) and a clear caveat that it does not guarantee safety, authentication, or correctness. No contradiction with annotations.

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?

Three concise sentences with front-loaded action, followed by output and limitation. No redundancy or filler; each sentence earns its place.

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?

Given a one-parameter tool with rich annotations and an output schema, the description covers the purpose, usage scenario, output format, and limitations. It is complete enough for an agent to decide when and how to invoke it correctly.

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?

Schema coverage is 100% for the single url parameter, and the schema already describes it as a public http(s) URL or bare domain. The description reinforces the 'unfamiliar URL' context but doesn't add new parameter-specific details beyond the schema. Baseline 3 is appropriate.

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

Purpose5/5

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

The description uses specific verbs ('Run', 'Returns') and clearly states the scope (reachability/response and security-header checks combined). It distinguishes from siblings by emphasizing the combined verdict and the preflight use case, which separates it from check_endpoint and inspect_security_headers.

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 specifies the intended use case ('for an unfamiliar URL or API before an AI agent trusts or acts on it') and provides limitations ('It does not prove that a service is safe, authenticated, or correct'). It doesn't explicitly name alternatives, but it implies when the combined check is appropriate versus individual checks.

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

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.