Skip to main content
Glama

Freigabe mit Agentenberechtigung

approval_decide_app
Destructive

App-internes Entscheidungs-Tool. Ein Aufruf gibt frei, wenn die verifizierte OAuth-Verbindung approval:self_approve trägt. Kartenansicht und cardNonce dienen nur als Vorschau-Beleg. Bei fehlender Berechtigung führt die Freigabe-Karte zum angemeldeten Browser. EN: Internal app decision tool. A call approves when the verified OAuth connection carries approval:self_approve. The card view and cardNonce serve only as preview evidence. When permission is absent, the approval card leads to the signed-in browser.

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": {
      "approvalId": "<approvalId>",
      "decision": "<decision>"
    },
    "name": "approval_decide_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
decisionYes
cardNonceNo
reasoningNo
approvalIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral facts: the OAuth scope required to authorize, that cardNonce is only preview evidence rather than an authority token, and what happens on permission failure — exactly the kind of auth/context detail annotations cannot express.

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?

The core points are front-loaded and each sentence carries content, but the full German/English duplication roughly doubles the length for no added information. Acceptable, not tight.

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 destructive four-parameter mutation with no output schema, the description covers the authorization gate and the nonce caveat, which are the hardest parts. It still leaves the meaning of approvalId/decision/reasoning and any indication of what a successful or rejected call returns unaddressed.

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

Parameters2/5

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 burden for all four parameters. It explains only `cardNonce` (preview evidence only) and says nothing about `approvalId`, `decision` (approve vs reject semantics), or `reasoning`, leaving three of four parameters undocumented anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the tool as an app-internal decision tool and says a call approves, so the verb and resource are present. However it never mentions the reject branch that the `decision` enum allows, and it does not explicitly distinguish this from the sibling `approval_decide` — the differentiation rests only on the phrase 'App-internes'.

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?

It gives a real precondition (the verified OAuth connection must carry approval:self_approve) and a fallback path (the approval card routes to the signed-in browser when permission is absent), which is useful guidance. But it never states when to pick this over `approval_decide` or `approval_submit`, leaving sibling selection to inference.

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.