Skip to main content
Glama

task_start

Mark a task as in progress, bind it to the current conversation, and retrieve handoff notes, active-file warnings, and optional git worktree setup.

Instructions

Start working on a task in this conversation: marks IN_PROGRESS, binds the conversation, and returns brief, upstream handoff_notes, active-file warnings, and optional git worktree command.

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": "task_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYesTask slug ID to start.
project_idNoOptional project ID (auto-resolved when omitted).
branch_nameNoOptional git branch name.
worktree_pathNoOptional dedicated git worktree path.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does well: it discloses the state mutation (IN_PROGRESS), a side effect (conversation binding), and the returned payload (handoff_notes, active-file warnings, optional worktree command). It omits what happens on repeat invocation, whether the state change is reversible, and any error/permission conditions.

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?

A single front-loaded sentence that packs the trigger, the mutations, and the return payload with no filler. It is dense but readable; a short clause separating effects from returns would improve scanability.

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 four-parameter state-mutating tool with no annotations and no output schema, the description covers the trigger, side effects, and return contents adequately. Missing error/idempotency behavior keeps it short of full completeness.

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 coverage is 100%, so all four parameters are already documented, and the description adds only the implication that branch_name and worktree_path drive the 'optional git worktree command' in the response. It adds no format, resolution, or precedence detail beyond 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 gives a specific verb+resource ('Start working on a task') and enumerates the concrete effects: marks IN_PROGRESS, binds the conversation, returns handoff notes/warnings/worktree command. It is clearly distinct from list/get-style siblings, though it does not explicitly contrast with close alternatives like task_update or task_plan.

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 implied by 'Start working on a task in this conversation', so an agent can infer this is the entry point before working. However, there is no explicit when-not guidance (e.g., what to do if the task is already in progress) and no named alternative such as task_update for changing state after work has begun.

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