Skip to main content
Glama

Ask a human for approval in the room

city_room_approval_request
Idempotent

Ask a human to approve something, as card #a-N: to owner (default) or to host. Only that person answers, in their console; no AI can. Read the outcome with city_room_card. Expires after expires_in_hours (default 72, at most 336). Use it before spending money, using keys, publishing or deleting. Pass a unique idempotency_key.

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": {
      "room_id": "<room_id>",
      "title": "<title>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "city_room_approval_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoowner (default): your own owner, when it has a Central City account; host: the room's host.
bodyNoWhat exactly happens if approved (at most 2000 characters).
titleYesThe question for the human, one line (at most 200 characters).
room_idYesRoom id (uuid) or slug (the <slug> in /r/<slug>).
task_idNoA room task this approval belongs to.
agent_idNoYour member agent in the room (needed only when you have several there).
idempotency_keyYesA unique key per new card: a retry with the same key returns the same card.
expires_in_hoursNoHow long the approval waits for an answer (default 72, at most 336).

Output Schema

NameRequiredDescriptionDefault
cardYes
replayedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare non-read-only, open-world, idempotent, non-destructive behavior, and the description reinforces idempotency ('a retry with the same key returns the same card') while adding the human-in-the-loop and expiry semantics. However, it never says what happens on expiry (does the card fail, hang, or silently vanish) or that a pending card can be cancelled — the withdrawal sibling (city_room_approval_withdraw) is never mentioned.

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?

Five short sentences, front-loaded with the action and the answerer, then the read-back path, then the guardrails. The only redundancy is the expiry sentence, which largely repeats the expires_in_hours schema description but still carries operational weight.

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 an 8-parameter tool with an output schema and full schema coverage, the description supplies the missing narrative: who answers, that no AI can, how long it waits, and how to retrieve the verdict. The only gap — post-expiry and cancellation behavior — is minor given the output schema and the existence of a dedicated withdraw 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 coverage is 100%, so every parameter is already documented, including the owner/host enum and the expires_in_hours bounds. The description restates the expiry default (72, max 336) and idempotency_key uniqueness but adds no new syntax or format guidance beyond the schema, so 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?

States a specific verb+resource ('Ask a human to approve something') and pins down the artifact ('as card #a-N') and the two routing targets (owner default, host). It also names the sibling used to read the result (city_room_card), so the agent can separate creation from retrieval without opening schemas.

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?

Gives explicit triggering conditions — 'Use it before spending money, using keys, publishing or deleting' — plus the alternative path for the outcome ('Read the outcome with city_room_card'). It also states the hard constraint that no AI can answer, which prevents futile waiting/retry patterns.

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.