Skip to main content
Glama

finish_task

Destructive

Close a task card by recording its result kind and evidence, moving it to done or review, canceling your active wait, and releasing your checkout.

Instructions

Close the card with its result: sets result_kind, moves the card to done (or review, when someone must accept a live result), writes the evidence as the closing comment, cancels your active wait and releases your checkout. Both result_kind and evidence are required; the existing move gates (closing comment length, linked MRs merged, open subtasks) still apply and their refusals are returned as is.

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>",
      "result_kind": "<result_kind>",
      "evidence": "<evidence>"
    },
    "name": "finish_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoTarget status: done or review. review means the result is live and awaits someone's acceptance.
task_idYesThe card to close (UUID or 6-12 hex short id).
turn_idNoOptional turn id within the session (max 200 chars), copied onto the outcome.
evidenceYesProof of each acceptance criterion — commands and their quoted output, max 4096 chars.
session_idNoOptional runner session id (max 200 chars), copied onto the recorded outcome and wait.
result_kindYesWhat the card delivered: change, defect, research, content or ops.
evidence_linksNoOptional URLs backing the evidence (MR, pipeline, artifact).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.7

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and non-idempotent, but the description goes well beyond them by naming the concrete side effects: the closing comment write, the wait cancellation, the checkout release, and the pre-existing gates (closing comment length, linked MRs merged, open subtasks) whose refusals are surfaced unchanged. It never contradicts the annotations. It does not say what a successful call returns, which is the remaining behavioral gap.

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?

Two sentences, front-loaded with the action and its consequences, then the preconditions. Every clause carries information — the side-effect list, the required-field note, and the gate exceptions — with no filler or repetition.

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 7-parameter destructive mutation with no output schema, the description covers side effects, required inputs and failure modes (gate refusals returned as-is), which is close to complete. The one omission is the shape of a successful result, which the agent cannot learn from any structured field here.

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 task_id, to, result_kind, evidence and the optional ids/links are all documented in the schema. The description mostly restates that result_kind and evidence are required and echoes the done/review meaning already present in the 'to' parameter, adding little semantic detail beyond the structured fields.

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 opens with a specific verb and resource ('Close the card with its result') and then enumerates the exact state changes that constitute closing: setting result_kind, moving to done/review, writing the evidence comment, cancelling the wait, releasing the checkout. This makes it unmistakable against siblings like move_task, update_task or release_task.

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?

It explains the done-vs-review branching ('review, when someone must accept a live result') and implicitly tells the agent it does not need to call release_task separately, since the checkout is released here. It stops short of explicitly naming alternative tools or stating when not to use it, so it is clear context rather than full routing guidance.

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