Skip to main content
Glama
Sign In

Verdict — Send anything. Get the truth.

by io.github.nrupala
OverviewDiscussionsAdmin

Check a suspicious message

check_message

Paste any suspicious text — a message, email, marketplace listing, job offer, investment pitch or link — and get a plain verdict (REAL / SUSPICIOUS / LIKELY SCAM) with every check shown, a warning score, what to do next, a signed verdict certificate, and a shareable verdict link. Content is processed, not stored.

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": {
      "text": "<text>"
    },
    "name": "check_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe full suspicious message or text to check (10–8000 characters).
subscriptionCodeNoOptional subscription code (Personal Pro / Team). The check draws on the plan’s monthly credit allowance instead of the free daily credits.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / subscriptionCode / description
      Previous value: -"Optional subscription code (Personal Pro / Team). The check draws on the plan’s monthly atom allowance instead of the free daily atoms."New value: +"Optional subscription code (Personal Pro / Team). The check draws on the plan’s monthly credit allowance instead of the free daily credits."
  2. Changed1 schema field changed
    • addedInput schema / properties / subscriptionCode
      Added value: +{
+  "description": "Optional subscription code (Personal Pro / Team). The check draws on the plan’s monthly atom allowance instead of the free daily atoms.",
+  "type": "string"
+}
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful traits: content is processed but not stored, and output includes a signed certificate and shareable link. It does not cover latency, failure modes, or explicit rate-limit/credit-exhaustion behavior, so it stops short of full transparency.

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

Conciseness4/5

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

A single well-formed sentence that front-loads the input contract before the output list. The output enumeration is long but every item is informative, and there is no filler.

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

Completeness4/5

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

With no output schema and no annotations, the description takes on both roles and does reasonably well: it names the verdict scale, the warning score, next steps, and the certificate/link artifacts, and states the data-handling policy. What is missing is sibling routing and any hint about credits being consumed per call.

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 description coverage is 100%, so both parameters are already documented, including the 10–8000 character range and the subscription code semantics. The description only hints at the subscription code's credit-allowance behavior, adding little beyond the schema; baseline 3 applies.

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?

States a specific verb (check) and resource (message/text) and enumerates the input types it covers, plus the exact verdict vocabulary returned. It is largely distinguishable from check_url, but the description explicitly invites pasting a 'link', which blurs the boundary with the URL-oriented siblings.

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

Usage Guidelines3/5

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

Usage is implied by the input enumeration ('paste any suspicious text'), but there is no explicit when-to-use/when-not guidance and no mention of the alternatives check_url or screen_urls. The inclusion of 'link' as an accepted input actively leaves the routing question open.

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

All Verdict — Send anything. Get the truth. toolsInspect
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.

Resources