Skip to main content
Glama

Caelara Labs Agent Safety

agent_output_validator

Validate LLM output: repair JSON, enforce schema, check grounding against a source, extract citations

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": {
      "output": "<output>"
    },
    "name": "agent_output_validator"
  }
}

Input Schema

NameRequiredDescriptionDefault
outputYesRaw LLM output
schemaNoJSON Schema subset to enforce
sourceNoSource text for grounding check

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.6/5.0
Behavior2/5

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

No annotations, so the description carries the full burden and falls short. It does not say whether 'repair' mutates the output or only reports problems, does not state the order in which checks execute, does not describe what happens when grounding fails, and gives no sense of the response shape for what is fundamentally a report-producing tool.

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 the resource stated first and the checks listed compactly; nothing is padded. The density comes at the cost of precision, but no sentence is wasted.

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?

For a three-parameter tool with a nested JSON Schema object, no annotations, and no output schema, an agent still cannot tell which validations will run for a given call or what the result looks like. The description should explain parameter gating and result reporting; it does neither.

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 the schema already defines output, schema, and source. The description implicitly maps schema to the enforcement step and source to grounding, which adds modest value, but it does not explain that these parameters are what activate or suppress individual checks.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (LLM output) and enumerates four operations: JSON repair, schema enforcement, grounding, citation extraction. But it never clarifies whether all four run every time or whether they are gated by optional parameters, which makes the actual purpose fuzzier than the enumeration suggests.

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?

No when-to-use guidance at all. Siblings json_auto_repair, schema_enforcer, hallucination_diff, and citation_extractor each appear to cover one of the listed operations, yet the description gives no rule for choosing this combined validator over them or over running them in sequence.

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