Skip to main content
Glama

List pending actions

list_pending_actions
Read-only

The AI actions currently parked for a human decision across the organisation (the twin of ankra chat actions list): the tool each would run, its description and risk, the cluster and session it belongs to, when it expires, how often the same action already failed, and the bill of materials of what approving would change. Use this when a user asks what is waiting on them or why an AI session is stuck. Read-only; decide_pending_action settles one.

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": "list_pending_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
cluster_idNoOnly actions on this cluster (UUID). Omit for the whole organisation.
session_cluster_onlyNoIn a cluster-bound conversation, only that cluster's actions (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so the 'Read-only' restatement adds nothing; however the description goes well beyond the annotation by disclosing what the payload contains, including expiry times, prior failure counts, and a bill of materials of the blast radius of approving. That is genuine behavioural context for a review-before-acting workflow. It doesn't discuss volume, pagination, or ordering of the returned 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?

The core purpose is front-loaded, and the colon-delimited field list is an efficient way to convey return contents. It is dense — the parenthetical CLI twin reference is arguably noise for an agent — but no sentence is wasted.

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?

With no output schema, the description takes on the burden of explaining what comes back, and it does so thoroughly while also covering scope, read-only safety, and the hand-off to the decision tool. For a two-parameter, zero-required read tool this is complete enough to invoke correctly on the first try.

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 both cluster_id and session_cluster_only are already documented, including the organisation-wide default. The description reinforces the organisation-wide scope but adds no extra meaning about the cluster-bound filtering parameter, so the schema is doing the heavy lifting and a baseline 3 applies.

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 names a specific verb and resource — AI actions parked for a human decision across the organisation — and then enumerates exactly what each entry carries (tool, risk, cluster/session, expiry, failure count, bill of materials). That is far more specific than the sibling list_* tools, and an agent can distinguish it from decision tools like decide_pending_action 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 Guidelines4/5

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

It states a concrete trigger ('when a user asks what is waiting on them or why an AI session is stuck') and routes the follow-up to decide_pending_action, which settles an action. What's missing is an explicit when-not condition, e.g. that this is not the tool for auditing historical or already-decided actions.

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.