Skip to main content
Glama
Sign In

Nutcracker

by com.heynutcracker
OverviewDiscussionsAdmin

Get task

get_task
Read-only

Where a task stands: running, needs_input (answer the question with reply), done, or failed. While running, progress names the step in flight (research, skill, ...; null while it thinks or writes the reply), its latest headline, and how many sources research has read. Returns the answer the latest reply ends with (a failed task: all it wrote) with evidence as links and [image card: name] where a card stands, the sources it cites, the skills it used, the other AI behind a take, the documents the task made (id, title, url), its images, video and sound with file urls and the credits each spent, and the image and video cards of the latest reply with their price: run one with generate once your human agrees to the price.

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": {
      "task_id": "<task_id>"
    },
    "name": "get_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
seenNoThe seen value from your last get_task: leaves out the reply, sources and cards you already read, and media that has not changed. Leave it out to read the cards and their prices again.
task_idYesA task_id, or a chat id from list_space.
all_sourcesNoList every source the task saw (sources_seen counts them), not only those the reply cites.
wait_secondsNoHold the call while the task, or once it is done its media, is still going, up to 45 seconds; it returns as soon as that ends. Use it instead of polling fast.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed world), so the bar is lower, and the description still adds real behavior: a failed task returns everything it wrote, incremental reads are governed by `seen`, cards and prices reappear when `seen` is omitted, and generation requires human agreement on price. The credit-spend and media-url disclosure is context an agent cannot get from annotations.

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

Conciseness2/5

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

It is front-loaded with the status states, which is the right priority, but the body is a single run-on sentence chaining semicolons across a long inventory of return fields. That density makes it hard to scan, and several clauses (evidence as links, image card notation) are reference detail that could be compressed.

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 full burden of describing returns, and it does cover status, in-flight progress, the answer text, evidence, sources, skills, generated cards, media urls, credits spent and pricing. Omissions are minor: nothing on error or unknown-task behavior, and no pagination note for large media sets.

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 the schema itself explains `seen`, `all_sources` and the 45-second `wait_seconds` hold in detail, so the schema does the heavy lifting. The description adds little parameter-specific meaning beyond restating the card/price effect of omitting `seen`, which is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and its state model up front ("Where a task stands: running, needs_input, done, or failed") and then enumerates what comes back, so an agent can tell this is a status-and-result fetch rather than a mutation. It is weaker on sibling differentiation: it never names start_task, the tool that creates the tasks it reads, though it does reference reply and generate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is only implied through the state machine: needs_input means "answer the question with reply", and after agreeing a price you "run one with generate". There is no explicit statement of when to call this versus list_space or how to sequence it after start_task, so routing is left to inference.

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

All Nutcracker toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources