Skip to main content
Glama

Tested authorization policy pack — Atom

Tested authorization policy pack

tested_authorization_policy_pack
Read-onlyIdempotent

Submit a declared authorization policy pack manifest (decision model, policy code, declared policies and their tests, rollout, decision logs, governance and enforcement); get a deterministic READY / NOT_READY / INSUFFICIENT_EVIDENCE verdict across six sections, including computed default-deny and per-policy test-coverage checks that name untested policies, with per-check evidence. Declared evidence only; no policy is executed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "tested_authorization_policy_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
packNoPolicy pack the verdict covers.
testsNoDeclared policy tests: policy id, kind (positive/negative/edge), and outcome.
rolloutNoRollout evidence (shadow mode, staged enforcement, rollback).
testingNoTesting-posture evidence (tests green, lint/format, role coverage declared).
policiesNoDeclared policies: ids, effect, and the tests that cover them.
governanceNoGovernance evidence (ownership, review, change control).
enforcementNoEnforcement evidence (bypass paths, silent-edit prohibition, fail-closed behaviour).
policy_codeNoPolicy-code evidence (composability, data/logic separation, versioning, explanations).
decision_logsNoDecision-log evidence (logging, explanation capture, retention).
decision_modelNoDecision-model evidence (enumerated decisions, input schema, default deny).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations covering read-only, idempotent, non-destructive, and closed-world behavior, the description discloses the deterministic verdict categories, six-section assessment, computed default-deny and test-coverage checks that name untested policies, and per-check evidence. It also adds the critical caveat that this is declaration-only analysis with no policy execution.

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?

The description is two sentences, front-loaded with the action and result, and then adds the most important caveat. The long parenthetical list is dense but necessary for describing the manifest scope, and there is no filler.

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?

For a complex ten-parameter evaluation tool with no output schema, the description supplies the outcome shape (verdict plus per-check evidence) and the evidence-only constraint. It could be slightly more explicit about malformed-manifest behavior or the exact section-to-field mapping, but it is otherwise complete enough for correct invocation.

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 the input schema already documents the ten manifest fields, including the declared-tests and declared-policies arrays. The description reinforces the manifest's evidence-only nature and lists several evidence areas, but it does not add field-level syntax or structure beyond the schema's descriptions.

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 action ('Submit a declared authorization policy pack manifest') and a specific result ('get a deterministic READY / NOT_READY / INSUFFICIENT_EVIDENCE verdict'). It names the resource and outcome clearly enough that an agent can distinguish this from a generic policy or authorization tool.

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?

The description makes the usage context clear: it evaluates declared evidence only, and no policy is executed. It does not list explicit exclusions or alternatives, but with no sibling tools and a highly specialized purpose, the intended use is well framed.

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.