Skip to main content
Glama
janorium-mcp

janorium-mcp

Official

Wait for runs to finish

wait
Read-onlyIdempotent

Block until specified job IDs finish or timeout, returning status and results; call again if still running.

Instructions

Blocks until every id finishes or timeoutSec (≤ 600) passes; an id still going comes back as {status:"RUNNING"} — call wait again. The result has the shape of the matching *_get tool: DRY_RUN → RunSummary; BACKTEST → RunSummary for one id, compact rows for several (then backtest_get the interesting one); OPTIMIZATION → optimization_get; RESEARCH_JOB → research_job_get. Progress is sent as MCP progress notifications when the client asks for them.

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": {
      "kind": "<kind>",
      "ids": "<ids>"
    },
    "name": "wait"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYes
kindYes
timeoutSecNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds real behavioral detail beyond that: blocking semantics, the 600s cap, the RUNNING sentinel return, progress notifications, and result shape per kind. Missing is what happens for unknown/expired ids or errors, so it is strong but not exhaustive.

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 blocking behavior and timeout, then the return shapes. Dense but mostly earning its place; the multi-clause sentence with arrows and nested parentheticals is harder to parse than a short bulleted mapping would be.

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 supplies the return shape per kind, which is the key missing piece for a tool like this. It also covers blocking, timeout, RUNNING retry and progress notifications, though error/invalid-id behavior and the 30-id batch ceiling are unaddressed.

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?

With 0% schema description coverage the description must carry the load. It explains `kind` thoroughly by mapping each enum value to its result shape, and restates the timeoutSec ≤ 600 constraint, but says little about `ids` beyond 'every id' (max 30 items, string-or-number accepted, and where ids come from are left to the schema).

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 blocking verb with its resource scope ('Blocks until every id finishes or timeoutSec ... passes'), and the per-kind result mapping makes clear how it relates to backtest_get/optimization_get/research_job_get. An agent can distinguish this from the *_get siblings without opening any 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?

Gives explicit follow-up guidance: if an id comes back as {status:"RUNNING"} then 'call wait again', and for multi-id BACKTEST results 'backtest_get the interesting one'. It does not state when to prefer this over repeatedly polling a *_get tool, which is the obvious alternative, so it stops short of full when/when-not guidance.

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