Skip to main content
Glama
@caelaralabs/mcp

@caelaralabs/mcp

caelara_agent_agent_output_validator

Validate and repair LLM output against a schema and source text, including JSON fixes, grounding checks, and citation extraction.

Instructions

[Agent Safety] Validate LLM output: repair JSON, enforce schema, check grounding against a source, extract citations Measured p50 11 ms, p95 15 ms (2026-11-21, benchmarks.caelaralabs.com). Calls https://agent.caelaralabs.com.

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": "caelara_agent_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 observedv1.0.1

TDQS

B3.3/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose two valuable behaviors: the tool makes an outbound call to https://agent.caelaralabs.com and it has benchmarked latency (p50 11 ms, p95 15 ms), which tells the agent it is a fast remote dependency. It omits critical behavior: whether 'repair' mutates and returns rewritten output, whether a grounding failure raises an error or is reported in the result, auth/rate-limit constraints, and what the response looks like.

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?

Capabilities are front-loaded in a single dense clause and the latency data follows, so the important information comes first. Minor waste and a formatting glitch ("extract citations Measured p50…") plus a benchmark URL that reads as marketing rather than operational guidance.

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?

This is a four-in-one composite with a nested-object parameter, no annotations and no output schema, yet the description says nothing about result structure or what happens when one of the four checks fails. For a multi-mode validator the agent needs to know how to interpret and act on the response, and that is entirely absent.

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%, so all three parameters (output, schema, source) are already documented in the schema; the baseline of 3 applies. The description adds no mapping between parameters and modes — notably that supplying 'source' enables grounding and supplying 'schema' enables enforcement — which would have been genuinely useful since those are optional.

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?

States a concrete verb and resource — "Validate LLM output" — and enumerates four concrete capabilities (JSON repair, schema enforcement, grounding check, citation extraction), so an agent knows what the call performs. It does not distinguish itself from clearly overlapping siblings (json_auto_repair, schema_enforcer, hallucination_diff, citation_extractor), so a '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 Guidelines3/5

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

The "[Agent Safety]" tag and the list of validation duties imply the use case (post-generation output validation), but the description never says when to prefer this composite over narrower tools, nor any preconditions such as 'requires a schema for enforcement to run'. Usage is inferable but not stated.

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

Deploy Server

Other Tools