Skip to main content
Glama

Caelara Labs Agent Safety

hallucination_diff

Flag answer sentences unsupported by the source text

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>",
      "answer": "<answer>"
    },
    "name": "hallucination_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
answerYesModel answer to check
sourceYesSource / ground-truth text

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden, and it discloses little: it does not say whether 'flag' means a boolean, a list of sentences, or a scored diff, nor whether the check is model-based or heuristic. It also omits prerequisites such as source text length limits. The word 'sentences' is the only real behavioral hint, implying sentence-level granularity rather than document-level.

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 front-loaded sentence with no filler or redundancy. It is efficient, though its brevity is under-specification rather than true conciseness, which is penalized in completeness instead.

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

Completeness2/5

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

With no annotations and no output schema, the description is the only source of behavioral and return-shape information, and it omits what the output looks like entirely. For a two-input analytical tool whose result format is ambiguous, this leaves a significant gap an agent cannot resolve elsewhere.

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 'source' and 'answer' are already documented in the schema, and the description's use of both terms adds no format or size constraints. Baseline 3 applies when the schema does the heavy lifting.

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 ('Flag') and a specific object ('answer sentences unsupported by the source text'), which tells an agent exactly what the tool evaluates. It stops short of distinguishing itself from a near-sibling such as agent_output_validator, but the narrowing to sentence-level grounding against source text is concrete.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no mention of when not to use it, and no reference to any alternative tool among the many validator/checker siblings. The agent must infer the use case entirely from the one-line purpose.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources