Skip to main content
Glama

Caelara Shield

shield_validate_output

Check model output before it is used: secret and PII leakage, exfiltration links, active content, dangerous shell patterns, optional schema and grounding checks (0.015 USDC per call)

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": "shield_validate_output"
  }
}

Input Schema

NameRequiredDescriptionDefault
outputYesRaw model output (max 200000 characters)
schemaNoJSON Schema subset to enforce
sourceNoSource text for a grounding check
system_promptNoYour system prompt, used only in this request to detect it being echoed back

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description must carry the burden. It usefully discloses per-call cost (0.015 USDC) and the detection categories, which is real added value. However it says nothing about the result shape, whether findings block anything, how failures are surfaced, or retention of the submitted output/system prompt -- material gaps for a safety-gate tool.

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?

A single front-loaded sentence that opens with the purpose and action, then enumerates the checks and ends with the cost. Every clause maps to either a capability or a parameter; nothing is redundant.

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?

There is no output schema, so the description is the only place an agent could learn what a validation call returns -- and it doesn't say whether the response is a verdict, a list of findings, or scores. For a tool whose whole purpose is producing an actionable judgment, that is a meaningful omission despite otherwise solid capability coverage.

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 every parameter is already documented in structured form; baseline is 3. The description adds only a light signal that the schema and grounding checks are optional, which corresponds to the two non-required parameters but does not add syntax or interaction detail beyond the schema.

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

Purpose5/5

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

The description states a specific verb and resource -- check model output before use -- and enumerates exactly what is detected: secret/PII leakage, exfiltration links, active content, shell patterns, plus optional schema and grounding checks. This reads clearly as an output validator, distinguishable from siblings like shield_scan_prompt or shield_audit_token.

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?

'Check model output before it is used' gives explicit timing/context for invocation, and the phrase 'optional schema and grounding checks' signals that two of the four parameters gate extra behavior. No exclusions or named alternatives are given, so it falls short of a 5, but the when-to-use signal is clear.

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