Skip to main content
Glama
Sign In

neonloops

by com.neonloops
OverviewDiscussionsAdmin

Approvals: decide

approvals_decide
DestructiveIdempotent

Approves or rejects one approval in neonloops: a run paused at an approval step or at an agent's tool call that asks first (run_id and node_id), or a question a bot asked in a conversation (approval_id). The run then resumes on the approved or rejected branch, with every side effect that branch has, or the bot answers the customer. It takes two calls: the first changes nothing and shows what would be decided, with a confirmation_token; the second, with the same arguments plus that token within 5 minutes, decides it, and a decision cannot be undone. Only the approval's assignee, a workspace owner or admin, or the person who started a test conversation may decide. An option_id that counts as the other decision is refused. Find what is waiting with approvals_list.

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": {
      "decision": "<decision>"
    },
    "name": "approvals_decide"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNoWith node_id: the paused run whose approval to decide. Not with approval_id.
commentNoOptional note recorded with the decision. Send it again, unchanged, on the confirming call.
node_idNoWith run_id: the paused step's id.
decisionYesApprove resumes the run on its approved branch, or answers the question with an approving option; reject takes the rejected branch or a rejecting option.
option_idNoWith approval_id only: which of the question's options to answer with; it must count as this decision. If it counts as the other one, the call is refused and names that decision: send it as decision, or omit option_id to answer with the first option for this decision.
approval_idNoA question a bot asked in a conversation. Not with run_id or node_id.
confirmation_tokenNoOmit to PREVIEW: nothing is changed and a confirmation token is returned. Call again with that token, and the identical arguments, to perform the action.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false; the description goes well beyond them by disclosing the two-call preview/confirm protocol, the 5-minute token expiry, the requirement to resend identical arguments, irreversibility, downstream effects (run resumes on the branch with all its side effects), and permission rules.

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?

Front-loaded with the core action and modes, and every sentence carries operative information. It is a single dense paragraph of long compound sentences, though, which makes the two-call protocol and permission rules harder to scan than a short structured list would be.

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

Completeness5/5

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

For a destructive, open-world mutation with no output schema, the description covers everything an agent needs: identifier combinations, decision semantics, preview/confirm sequencing with token lifetime, refusal behavior, and authorization constraints. Nothing material is left to inference.

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% and each parameter description already spells out mutual exclusivity and the option_id fallback, so the description mostly restates what the schema carries. It does tie the parameters together narratively (same arguments plus token on the second call), which is why it holds the baseline rather than falling below it.

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?

States a specific verb pair (approves or rejects) and a specific resource (one approval in neonloops), then enumerates the two target modes: a paused run step keyed by run_id/node_id and a bot question keyed by approval_id. An agent can distinguish it from approvals_list and runs_get without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes discovery to approvals_list ("Find what is waiting with approvals_list") and specifies which identifier set selects which mode. It also states the authorization precondition (assignee, workspace owner/admin, or test-conversation starter) and the refusal condition on a mismatched option_id.

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

All neonloops toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources