Skip to main content
Glama

Kosmodrom

by ai.kosmodrom
OverviewDiscussionsAdmin

task_done

Destructive

Finishes the work on a taken task (shared team data): outcome, result, message and usage in one call. Outcomes: done (the work is done or accepted and the task moves on), return (sent back with a required message, including bugs in work returning to testing), wait (the part is done, the task waits in the queue), close. The server makes the transition, closes the worklog and calculates the cost of the work from the difference of the start and end snapshots; done returns the feature plan.

Input Schema

NameRequiredDescriptionDefault
IDNoTask ID; preferred over key.
keyNoTask number without #, if the ID is unknown.
runYesSession counters accumulated since its start, as at the start of the work, at the end of the same session; limits - subscription limits at the end (window to utilization 0-1 and resetsAt in ISO 8601), accuracy 0-1 - counters accuracy, 1 by default.
gistNoGist: one or two plain-text sentences "problem → solution", up to 300 characters, without Markdown, links or task keys, in the language of the workspace data; updated if the solution changed.
resultNoResult: in work - the whole result field (Markdown in the language of the workspace data, HTML is rejected; replaces the whole field), the tester's "QA verification" block is kept by the server; in testing - only that block, placed by the server at the end of the field; not accepted at approval and review.
messageNoMessage to the task chat: required for a return (what to fix); otherwise only what people need to know.
outcomeYesOne of the outcomes returned when the task was taken.
moduleIDsNoFull new list of modules actually touched.
attachmentsNoFile IDs (fid) of uploaded files, up to 5, attached to the message.
closeReasonNoClosing reason, required for close: resolved, notDoing, notReproducible, notBug or duplicate; the explanation goes in the message.
componentIDsNoFull new list of components actually touched.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / result / description
      Previous value: -"Result: in work - the whole result field (Markdown in the language of the workspace data, HTML is rejected; replaces the whole field); in testing - only the \"QA verification\" block placed at the end of the field; not accepted at approval and review."New value: +"Result: in work - the whole result field (Markdown in the language of the workspace data, HTML is rejected; replaces the whole field), the tester's \"QA verification\" block is kept by the server; in testing - only that block, placed by the server at the end of the field; not accepted at approval and review."
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, so the mutation is known. The description goes beyond them by disclosing server-side effects: it makes the transition, closes the worklog, and calculates cost from the start/end snapshots, plus that 'done' returns the feature plan. Missing only notes on reversibility/failure modes.

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?

The core action is front-loaded in the first clause, followed by the outcome list and server behavior. Dense but each sentence carries information; the long outcome enumeration is justified by the four-way branch the agent must pick.

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 an 11-parameter mutation with nested objects and no output schema, the description covers purpose, outcome branching, and server-side effects adequately, and the schema fully documents parameters. It leaves the prerequisite (task must already be taken) and any error/rollback behavior to inference.

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 100%, so the baseline is 3. The description earns a bump by giving the meaning of each outcome enum (done/return/wait/close) and the side effect tied to 'done', which the bare enum listing does not convey; it does not otherwise add syntax beyond the schema.

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 and resource ('Finishes the work on a taken task') and prefaces it with the scope ('shared team data'). The phrase 'a taken task' implicitly routes the agent away from task_take/task_create/task_update, so the tool's role in the flow is clear without opening any 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?

Enumerates the four outcome variants with the condition that selects each (done = accepted and task moves on; return = sent back with a required message; wait = part done, waits in queue; close). That is strong in-tool selection guidance, but it never names a sibling alternative or states a prerequisite (e.g. task_take must run first) explicitly.

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

All Kosmodrom toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources