Skip to main content
Glama

Caelara Labs Agent Safety

agent_input_firewall

Scan untrusted input: injection risk + PII redaction + sanitized text + allow/review/block verdict

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": {
      "text": "<text>"
    },
    "name": "agent_input_firewall"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesUntrusted input text
redact_piiNoRedact PII in sanitized output (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose something valuable the structured data lacks: that the call returns a tri-state verdict (allow/review/block) plus sanitized text. However, it says nothing about what drives block vs. review, whether the operation has side effects, latency, or whether the call is safe to repeat.

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 compact fragment, front-loaded with the action and followed by a terse enumeration of returns; nothing is padded. The telegraphic style (plus signs, no verb for the second clause) slightly hurts readability but wastes no words.

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?

For a two-parameter tool with no output schema and no annotations, the description at least tells the agent what the response contains. It falls short on verdict semantics and usage boundaries, which are exactly the gaps the missing annotations leave open.

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 both parameters are already documented, establishing a baseline of 3. The description mentions PII redaction as an output capability but does not clarify that redact_pii is a toggle controlling that output, so it adds no meaning beyond the schema.

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?

Names a specific verb and resource ("Scan untrusted input") and enumerates the concrete outputs (injection risk, PII redaction, sanitized text, verdict), so the agent knows exactly what comes back. It does not contrast itself with overlapping siblings such as prompt_injection_scanner or pii_redactor, so differentiation is left to the reader.

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 phrase "untrusted input" implies the usage context (untrusted or externally-sourced text), which is a real scoping signal. But there is no explicit when-to-use vs. when-not, and no mention of the obvious overlapping siblings, so the agent must infer whether to call this or the single-purpose scanner/redactor tools.

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