llm-assure-mcp

send_probe

Send a custom prompt or multi-turn history to a target chatbot and run quick checks for refusal, system-prompt canary leaks, and PII or secret exposure during adaptive red-teaming.

Instructions

Send one custom prompt (optionally after prior turns) to the target and run quick checks.

Use this for adaptive, multi-step red-teaming: read the reply, then craft the next attempt. Quick checks report refusal, system-prompt canary leaks and PII/secrets.

Args: prompt: the message to send. target_file / target: the system under test. history: earlier turns as [{"role": "user"|"assistant", "content": "..."}].

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": {
      "prompt": "<prompt>"
    },
    "name": "send_probe"
  }
}

Input Schema

Name	Required	Description	Default
`prompt`	Yes
`target`	No
`history`	No
`target_file`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 13, 2026

TDQS

A3.6/5.0

Behavior3/5

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

There are no annotations, so the description carries the full burden. It usefully discloses that each call runs checks for refusal, system-prompt canary leaks and PII/secrets, but says nothing about side effects on the target system, authentication or target-selection requirements, rate limits, or failure behavior when the target is unreachable.

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?

The purpose and usage condition are front-loaded in the first two sentences, and the Args block is terse and scannable. Minor redundancy in restating parameter names, and the paragraph break before 'Use this' is slightly awkward, but nothing is wasted.

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

Completeness3/5

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

With an output schema present, the description does not need to document return values, and it wisely just names what the quick checks report. Still, for a tool that reaches out to a live target, the missing pieces are target resolution semantics and what happens on connection or parse failure, leaving an agent to guess.

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 0%, so the description must compensate, and it partly does: prompt is identified as the message, history is given a concrete shape ([{"role": "user"|"assistant", "content": "..."}]). However, 'target_file / target' is described only as 'the system under test', which does not explain what the target object contains or how the two parameters interact or which wins.

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 states a specific verb and resource: send a custom prompt to a target and run canned safety checks, with an optional history of prior turns. That is enough for an agent to distinguish it from a batch-oriented sibling like run_assessment, though no sibling is named explicitly.

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 a clear positive condition ('adaptive, multi-step red-teaming: read the reply, then craft the next attempt'), which is exactly the when-to-use signal an agent needs. It stops short of naming the alternative tool or stating exclusions (e.g. use run_assessment for fixed suites), so it is not a 5.

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

Deploy Server