Skip to main content
Glama

List everything waiting for your approval

approvals_list
Read-onlyIdempotent

[read-only] The approvals inbox: everything that waits on the user's decision, in one list. kind "ad_budget" is an ad agent's request above the owner's ceiling (a spend cap, a spending limit, a campaign budget), with amount, changes and a one-line summary of before → after; it shows only with the approvals:decide scope, to an owner or admin, and never a request this same connection made. kind "manual" or "workflow" is held content (needs approve or approvals:decide, Agency plan). Read summary to the user before deciding anything. (Wraps GET /api/v2/approvals.)

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": "approvals_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
statusNoFormat: string; e.g. "pending". Status to select or set.pending
brandIdNoFormat: string; e.g. "brandId_123". Brand identifier from list_brands; use a real ID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / brandId / description
      Added value: +"Format: string; e.g. \"brandId_123\". Brand identifier from list_brands; use a real ID."
    • addedInput schema / properties / status / description
      Added value: +"Format: string; e.g. \"pending\". Status to select or set."
  2. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral facts: the hidden-result rule ("never a request this same connection made"), the scope and role requirements, and the plan gate on manual/workflow kinds. What it omits is ordering, pagination, and volume/size expectations for what is described as an "everything" list.

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?

Purpose and the read-only marker are front-loaded, and the bracketed API wrapper is correctly relegated to the end. The middle is dense with quoted field names and parenthetical synonym strings ("a spend cap, a spending limit, a campaign budget") that cost length without adding precision.

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 no output schema, the description carries the burden of describing return content and does so for the ad_budget shape (amount, changes, summary as before → after). The `status` filter's interaction with the described 'pending' framing is not spelled out, and there is no mention of result volume — the remaining gaps for a two-parameter list tool.

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 100% and both parameters (`status`, `brandId`) are documented in the schema, so the baseline is 3. The description instead spends its words on `kind`, `amount`, `changes` and `summary` — which are response fields, not parameters — creating mild ambiguity about whether `kind` is filterable here. Useful context for the return shape, but no added meaning for the actual inputs.

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?

Opens with a specific verb-resource-definition: "The approvals inbox: everything that waits on the user's decision, in one list." It then enumerates the distinct `kind` values (ad_budget, manual, workflow) so an agent knows exactly what universe of objects comes back, which distinguishes it cleanly from the sibling `approvals_decide`.

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 real gating conditions: ad_budget entries require the `approvals:decide` scope and an owner/admin caller; manual/workflow entries need `approve` or `approvals:decide` on the Agency plan. The closing directive "Read `summary` to the user before deciding anything" implies a paired decision tool without naming it, so routing is inferred rather than explicit.

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.

Resources