Skip to main content
Glama
TrialRun MCP

TrialRun MCP

by kostadindev

Scan text for restricted data

check_text

Scan outgoing AI answers, drafts, or pasted text for credentials, card numbers, personal details, and sensitive terms before display or saving, returning labels and redacted snippets.

Instructions

Scan an outgoing AI answer, a draft, or text the user pasted, for restricted data (credentials, cards, personal details, sensitive terms) before it is shown or saved. Hits are logged as leaks into the AI answer. Returns labels and redacted snippets only.

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_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
recordNoLog hits as answer leaks (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the behavioral load and does meaningful work: it discloses a side effect (hits are logged as leaks into the AI answer) and a data-minimization guarantee (only labels and redacted snippets are returned). The side effect is stated as unconditional, which slightly under-describes the record toggle, and it says nothing about permissions, scan determinism, or failure behavior.

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?

Two sentences, each earning its place: first the action and its inputs, then the side effect, then the return contract. It is front-loaded so the agent learns what the tool does before any caveats, with no filler wording.

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?

For a two-parameter tool with no annotations and no output schema, the description covers purpose, side effect, and return shape (labels plus redacted snippets), which is enough to call it correctly. It is only incomplete around the record=false path and permission or failure conditions.

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 50%: the record parameter carries its own schema description, while text has none. The description partially compensates by specifying which kinds of text to scan, but it does not explain that record=false suppresses the leak logging it describes — the reader must reconcile "Hits are logged" with the toggle themselves. Marginal value added, so baseline 3.

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 uses a specific verb ("Scan") against a specific resource (an outgoing AI answer, a draft, or pasted text) and enumerates what it looks for (credentials, cards, personal details, sensitive terms). What it does is unambiguous. It stops short of any explicit differentiation from sibling tools such as get_report or read_file, so it lands at 4 rather than 5.

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?

The phrase "before it is shown or saved" gives a clear trigger condition, and the enumerated input types (outgoing AI answer, draft, pasted text) tell the agent which payloads qualify. There are no explicit exclusions or named alternatives to route away from, so it is clear context without full when/when-not guidance.

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