CutGPT Research & Fact-Check

Check a draft against its source

check_grounding

Read-onlyIdempotent

Flag specifics in a draft that never appear in its source: quotes, numbers, money, percentages, dates, credentials, and names.

Deterministic and instant (no AI). Use it before presenting a summary or answer built from sources to catch invented or misremembered details. Each flag includes the sentence it came from.

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": {
      "source": "<source>",
      "draft": "<draft>"
    },
    "name": "check_grounding"
  }
}

Input Schema

Name	Required	Description	Default
`draft`	Yes	The summary, answer, or rewrite to verify.
`source`	Yes	The source text the draft should be based on (article, transcript, notes).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds genuinely new traits: the check is deterministic, instant, and uses no AI. That tells the agent results are reproducible and not model-generated, which is not inferable from 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 short sentences, front-loaded with the capability and detection categories, then usage timing, then a return-value note. No filler or repetition.

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?

Output schema exists so return format needn't be explained, yet the description still notes each flag carries its originating sentence. Crucially it scopes the tool as literal, deterministic matching ('no AI'), preventing the agent from assuming it validates semantic accuracy.

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% and both parameters are documented in the schema, so the schema does the heavy lifting. The description only restates the draft/source relationship conceptually and adds no format, size, or length guidance.

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?

States a precise verb (flag) and resource (specifics in a draft absent from its source), then enumerates exactly what counts as a specific: quotes, numbers, money, percentages, dates, credentials, names. That enumeration cleanly separates it from generic siblings like text_stats or find_fact_checks.

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?

Gives explicit timing guidance: 'Use it before presenting a summary or answer built from sources.' It does not name a sibling alternative or state when NOT to use it, so it stops short of full routing guidance.

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

All CutGPT Research & Fact-Check 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.

Resources

Need Help?