Skip to main content
Glama
@caelaralabs/mcp

@caelaralabs/mcp

caelara_api_prompt_firewall_structurer

Scans prompt text for injection attacks and PII, then returns a structured result for firewall decisions. Use strict mode and context to tailor prompt screening.

Instructions

[Web Intelligence] Scan a prompt for injection/PII and return a structured form Measured p50 12 ms, p95 15 ms (2026-11-21, benchmarks.caelaralabs.com). Calls https://api.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": {
      "prompt": "<prompt>"
    },
    "name": "caelara_api_prompt_firewall_structurer"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYesPrompt text
strictNoStrict mode
contextNoAdditional context

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full burden and mostly spends it on latency benchmarks and the API hostname rather than behavior. It never says whether the prompt is stored or logged, whether PII is reported or removed, how findings are surfaced, or what auth/rate limits apply.

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?

Very short and front-loaded with the purpose in the opening clause, so an agent can act on it quickly. The trailing benchmark and endpoint sentences are low-value filler, and the first sentence is missing terminal punctuation, which slightly muddies the boundary between purpose and telemetry.

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 3-parameter security-screening tool with no annotations and no output schema, the description leaves critical gaps: the return shape of the "structured form" is never characterized, and the effect of strict/context is unexplained. It is not enough to call it correctly and interpret the result with confidence.

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% and all three parameters are documented in the schema, so the baseline applies. The description adds nothing about what "strict" mode changes or what "context" influences, but it is not required to under full schema coverage.

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?

"Scan a prompt for injection/PII and return a structured form" gives a specific verb and resource, so the agent knows this is prompt security screening. However, it never differentiates itself from obvious siblings like caelara_agent_prompt_injection_scanner or caelara_agent_pii_redactor, and "structured form" is left undefined, so the boundary of the tool remains fuzzy.

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 at all: no prerequisites, no mention of when to pick this over the injection scanner or PII redactor siblings, and no note about whether it detects or redacts. The agent must infer everything about fit 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.

Deploy Server

Other Tools