Skip to main content
Glama
Brilliant MCP

Brilliant MCP

Official

wait

Read-onlyIdempotent

Blocks until a background edit, export, or render job finishes and returns its result instead of polling; if it is still running, call it again.

Instructions

Wait for a long call to end, instead of sleeping and checking. job is the id from a background: true call of edit, export or render_ui, or the requestId (or job: line) of an edit, also one whose call timed out on your side. Blocks until the job is done or failed and answers its result, the answer the call itself would have given. running means your timeout ran out and the job goes on: call wait again. superseded means the job ended with an earlier app run or its answer aged out: read the canvas. If this call cannot reach the app at all, the app is down: run scripts/mcp-wait-up.sh.

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": {
      "job": "<job>"
    },
    "name": "wait"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesThe job id.
timeoutNoSeconds to block, default 120, at most 280. 0 answers the state now.
sessionIdNoYour session id from init: a requestId is per session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/non-destructive annotations, the description explains blocking behavior, timeout semantics, status outcomes, result equivalence, and a failure fallback. This is unusually rich behavioral context for a wait tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, and each sentence adds actionable information about input origin, blocking, status handling, or failure recovery. There is no filler or repetition.

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?

There is no output schema, so the description must explain outcomes, which it does through `running`, `superseded`, failure/down states, and result semantics. That is sufficient for an agent to invoke and follow up correctly.

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

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful context for `job`: where to get it, how requestId and `job:` line values relate, and that it can refer to calls that timed out locally.

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 states a specific verb and resource: wait for a long call/job to end, explicitly contrasted with sleeping and checking. It also names the sibling-originated jobs it works with (edit, export, render_ui), so an agent can distinguish it from related tools.

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?

It gives explicit usage conditions: job ids from `background: true` calls or requestIds from edit, including calls that timed out. It also tells the agent what to do for `running`, `superseded`, and unreachable-app outcomes.

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