Skip to main content
Glama

FrankKi

by app.frankki
OverviewDiscussionsAdmin

Freigabe entscheiden

approval_decide
Destructive

Gibt eine wartende Freigabe frei oder lehnt sie ab. 'approve' ist nur erlaubt, wenn dieser OAuth-Verbindung die zusätzliche Berechtigung approval:self_approve ausdrücklich erteilt wurde. Fehlt diese Berechtigung, öffnet der Mensch den zurückgegebenen approvalUrl und entscheidet im angemeldeten Portal. approval:decide bleibt ebenfalls erforderlich. Bei Freigabe durch den Agenten geht der Brief nach 10 Minuten raus und kann bis dahin mit order_cancel gestoppt werden. EN: Approves or rejects a pending approval. 'approve' is allowed only when this OAuth connection was explicitly granted the additional approval:self_approve scope. When that scope is absent, the human opens the returned approvalUrl and decides in the signed-in portal. approval:decide is also required. An agent approval dispatches after 10 minutes and can be stopped with order_cancel until then.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commentNo
decisionYes
reasoningNo
approvalIdYes
clientOrderIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / user_saw_preview
      Removed value: -{
-  "description": "Bestaetigung, dass du dem Menschen die Vorschau-PDF, den genauen Preis und die Versandart gezeigt und seine Zustimmung eingeholt hast. Fuer eine Freigabe erforderlich. EN: Confirmation that you showed the human the preview PDF, the exact price and the delivery type and obtained consent. Required to approve.",
-  "type": "boolean"
-}
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only flag destructiveHint/readOnlyHint; the description adds substantial behavioral context beyond that: dual OAuth scope requirements, a human-in-the-loop fallback path via approvalUrl, a 10-minute dispatch delay after agent approval, and the cancellability window via order_cancel. These are exactly the operational traits an agent needs before committing a destructive action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded and dense, but the entire text is duplicated in German and English, roughly doubling length for the same information. The scope rule, the human fallback, and the cancellation window are all useful, but the bilingual mirroring is pure redundancy.

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 destructive mutation with no output schema, the description covers the essentials: permission prerequisites, the human fallback, post-approval timing, and reversibility. Minor gaps remain around the undocumented comment/reasoning params and no contrast with the _app sibling.

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 0%, so the description must carry the load. It clarifies the decision enum semantics ('approve' vs 'reject') and references the returned approvalUrl, but says nothing about comment, reasoning, approvalId, or clientOrderId, leaving three of five parameters undocumented anywhere.

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 clear verb-resource pair ('Gibt eine wartende Freigabe frei oder lehnt sie ab' / approves or rejects a pending approval) with the decision alternatives spelled out. However, it never differentiates itself from the sibling approval_decide_app, which appears to be a near-namesake, leaving an agent to infer the distinction.

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?

Gives explicit conditional guidance: 'approve' is only permitted when the OAuth connection carries approval:self_approve, otherwise the human must open the returned approvalUrl, and approval:decide is also required. It also names order_cancel as the follow-up escape hatch within 10 minutes. It stops short of stating when to prefer this tool over approval_decide_app.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FrankKi toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources