Skip to main content
Glama
Sign In

Kosmodrom

by ai.kosmodrom
OverviewDiscussionsAdmin

task_relation_update

Creates or changes a relation between two tasks or bugs. The role is relative to the current task (key), with the names used in the task's relations: dependencies - the current task waits for the other; blockedTasks - the other waits for it; duplicateOf / duplicates; regressionOf / regressions; foundDuring / findings; related - neutral. For a bug, foundDuring is the task during which it was found and regressionOf the task that introduced the defect (by git history only). Without a relation of that role one is created (desc - explanation); an existing one gets newRole and desc. Moving it away from dependencies / blockedTasks unblocks the waiting task with notifications, as in the web app.

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": {
      "key": "<key>",
      "otherKey": "<otherKey>",
      "role": "<role>"
    },
    "name": "task_relation_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesCurrent task number — the one the role refers to
descNoExplanation; null or empty string — remove; omitted — unchanged
roleYesRelation role relative to the current task, as in its relations
newRoleNoNew role of an existing relation; omitted — unchanged
otherKeyYesRelated task or bug number

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / desc / description
      Previous value: -"New explanation; null or empty string — remove; omitted — unchanged"New value: +"Explanation; null or empty string — remove; omitted — unchanged"
    • removedInput schema / properties / key / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / key / minimum
      Removed value: --9007199254740991
    • changedInput schema / properties / newRole / description
      Previous value: -"New role relative to key; omitted — unchanged"New value: +"New role of an existing relation; omitted — unchanged"
    • removedInput schema / properties / otherKey / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / otherKey / minimum
      Removed value: --9007199254740991
    • changedInput schema / properties / role / description
      Previous value: -"Current role of the relation"New value: +"Relation role relative to the current task, as in its relations"
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-open-world mutation, so the safety profile is covered. The description adds real behavioral context beyond that: moving a relation away from dependencies/blockedTasks 'unblocks the waiting task with notifications, as in the web app.' It does not state permissions, reversibility, or return shape.

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?

Front-loaded with purpose, and the long role enumeration earns its space because each value needs disambiguation. It is a single dense paragraph, though; splitting the role list into a structured form would improve scannability.

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 5-parameter mutation tool with no output schema, the description covers role semantics, create-vs-update behavior, and side effects. It omits what the tool returns and any error/permission context, which an agent calling a write operation would benefit from.

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

Parameters5/5

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

Schema coverage is 100%, so baseline is 3, but the description goes well beyond the schema by defining directional semantics for each role ('dependencies - the current task waits for the other; blockedTasks - the other waits for it') and by explaining bug-specific meanings of foundDuring/regressionOf. This meaning is not available from the raw enum.

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 first sentence gives a specific verb and resource: 'Creates or changes a relation between two tasks or bugs.' It is immediately distinguishable from the sibling task_relation_delete, and the body clarifies it is an upsert (create when absent, mutate when present).

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 explains the create-vs-update condition ('Without a relation of that role one is created... an existing one gets newRole and desc') and the meaning of every role value, which effectively tells an agent when to pick each. It stops short of naming alternatives or exclusions (e.g. routing to task_relation_delete or explaining prerequisites).

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
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources