Skip to main content
Glama

task_claim

Claim, release, hand off, accept, or take over a task's mutation scope to coordinate parallel agents and prevent conflicting edits.

Instructions

Mutation-scope claims (operator methodology). Claim once when you start a scope and release once when you stop; task_update keeps the claim alive in between. claim: take a lease (default 30 min; pass minutes for long work). release: give it up. handoff: keep it until to accepts (needs note with state + next action). accept: take a handoff addressed to your lane. takeover: take a claim from a session confirmed gone (needs note with reason).

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": {
      "id": "<id>",
      "action": "<action>"
    },
    "name": "task_claim"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesTask id: the 8-character id shown in task_context/task_list (full UUID also works).
toNohandoff target lane, e.g. "Operator_4", or "unassigned".
cwdNoSession folder (absolute path). Filled in by the OpenCode plugin; other clients pass the working folder.
noteNo
actionYes
minutesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the lease model, the 30-minute default, the ability to extend via minutes for long work, and the state-transfer semantics of handoff/accept/takeover including required note contents. It does not say what happens when a lease expires, whether claim fails when the scope is already claimed, or what happens to an unaccepted handoff, which are the main behavioral gaps.

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 description is dense and front-loaded: the scoping statement and the claim/release lifecycle come first, followed by compact labeled glosses for each action. Every clause carries distinct information, and no sentence restates the schema or the name.

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 six-parameter mutation tool with no annotations and no output schema, the description covers the action space, the lease model, and the note requirements well enough to call it correctly. The remaining gaps are failure/expiry behavior and the `cwd` parameter, which are relevant but secondary to selecting and invoking the tool.

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 only 50%, so the description has to compensate, and it largely does: it gives meaning to `note` (state + next action for handoff, reason for takeover), explains `minutes` as a lease duration with a 30-minute default and a 'long work' use case, and defines each `action` enum value. `to` is only lightly glossed ('addressed to your lane') and `cwd` is not addressed at all, leaving a partial 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?

The description names a specific verb+resource ('Mutation-scope claims') and then enumerates the five concrete operations (claim, release, handoff, accept, takeover) with a one-line gloss each. It also explicitly contrasts itself with a sibling, noting that task_update keeps the claim alive rather than being the claim tool, so an agent can route correctly without opening the 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?

Timing guidance is explicit for the core lifecycle: 'Claim once when you start a scope and release once when you stop,' with per-action preconditions for handoff ('needs note with state + next action'), takeover ('from a session confirmed gone'), and accept ('addressed to your lane'). What is missing is an explicit statement of when not to use this tool at all, or a named alternative for cases where a claim already exists.

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