Skip to main content
Glama

Coline

Take a task

take_task

Claims a task for this agent so no other agent works on it, and moves it to in progress if it hadn't started. Fails when another agent holds it. The claim lapses after two hours without a call about the task, and the task goes back as it was. Then say where you are with set_task_status_line, attach your work with attach_to_task, and finish with finish_task, or let it go with release_task.

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": {
      "workspace": "<workspace>",
      "taskboardId": "<taskboardId>",
      "taskId": "<taskId>"
    },
    "name": "take_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskIdYes
workspaceYesWorkspace slug from workspaces.list, e.g. "acme".
taskboardIdYes

Output Schema

NameRequiredDescriptionDefault
takenYes
identifierYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing exclusivity semantics, failure on contention, a two-hour claim lease, and automatic reversion of the task if the agent stops calling about it. These are non-obvious state-machine behaviors an agent cannot infer from structured fields.

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?

Core action and its side effects are front-loaded, and each sentence carries distinct operational information. The final sentence is a slightly long enumeration of follow-up tools, and 'the task goes back as it was' mildly restates the lapse clause, but nothing is padding.

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?

For a non-idempotent mutation with an output schema, annotations, and three required params, the description covers the mutation's consequences, contention behavior, lease expiry, and next steps. Its only meaningful omission is any explanation of the identifier parameters, which the schema also fails to document.

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

Parameters2/5

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

Schema description coverage is only 33% – just the workspace slug – so taskId and taskboardId are undocumented in both schema and description. The description adds no meaning about identifiers, formats, or whether taskId must come from a prior find_task/get_task result, leaving a real gap.

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 (claims) on a specific resource (a task) plus the two concrete effects: exclusive ownership for this agent and a move to in-progress. It is immediately distinguishable from sibling mutators like finish_task or release_task, which it even names.

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?

The description gives the after-claim workflow explicitly, pointing to set_task_status_line, attach_to_task, finish_task, and release_task as the follow-up or opt-out paths. It also states a failure condition (another agent holds it), which tells the agent what to expect rather than when to prefer an alternative such as next_task.

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.

Resources