Skip to main content
Glama
PAARA Connector Audit

PAARA Connector Audit

score_connector

Scores an AI connector against the seven PAARA factors and returns Low-to-Critical risk bands, flagging restricted controls, to support connector governance decisions.

Instructions

Score an AI connector with the PAARA seven-factor rule. Give the seven factor codes from the connector's documentation: F1 sensitive-data reach, F2 cross-system aggregation, F3 non-user-bound credentials, F4 absent logging, F5 prompt-injection exposure, F6 external sharing, F7 agentic action capability. Each code is Y (documented), N (documented absent) or U (documentation silent). Returns lower/upper score bands (Low/Moderate/High/Critical); set restricted=true if a documented write-limiting control applies, for restricted bands.

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": {
      "F1": "<F1>",
      "F2": "<F2>",
      "F3": "<F3>",
      "F4": "<F4>",
      "F5": "<F5>",
      "F6": "<F6>",
      "F7": "<F7>"
    },
    "name": "score_connector"
  }
}

Input Schema

NameRequiredDescriptionDefault
F1Yes
F2Yes
F3Yes
F4Yes
F5Yes
F6Yes
F7Yes
nameNoConnector name (optional label).
restrictedNoTrue if a documented write-limiting control applies.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.1

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose the return shape (lower/upper score bands in Low/Moderate/High/Critical) and the effect of restricted=true, but it never says this is a pure, side-effect-free computation, nor whether results are deterministic or persisted.

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 dense paragraph that front-loads the action and framework, then enumerates the factors that the schema leaves opaque. The factor list is necessary rather than padding, though the closing clause about restricted bands is compressed almost to the point of ambiguity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With nine parameters, 22% schema coverage, and no output schema, the description does the heavy lifting: it explains inputs, value encoding, and return bands. What remains unclear is the mapping between factors and bands and what "restricted bands" concretely changes in the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 22%, so the description must compensate, and it largely does: it expands all seven cryptic F1–F7 codes into named factors and defines the Y/N/U value semantics that the bare enum does not. The optional name label and the meaning of "restricted bands" are left comparatively thin.

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 specific verb and resource ("Score an AI connector") and names the scoring framework (PAARA seven-factor rule), which distinguishes it from the sibling lookup_connector and list_connectors by implication. It does not explicitly contrast with those siblings, but the computational nature of the operation is unmistakable.

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 description establishes the precondition that the seven codes must come from the connector's documentation, which is useful usage context. However, it never states when to choose this over lookup_connector or list_connectors, nor what to do when documentation is missing beyond the U code.

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