Frostbyte

update_task

DestructiveIdempotent

Update fields on an existing task. Resolve requested release/area names within the project and set real releaseId/areaId fields; notes do not assign placement. Verify with get_task. Changed fields are audited with before/after values. Marking done with incomplete subtasks requires completionPolicy. Pass null for releaseId to move to Backlog, or for areaId to clear the area. After moving tasks into or out of a release, check its description still matches its scope.

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": {
      "projectId": "<projectId>",
      "taskId": "<taskId>",
      "context": "<context>"
    },
    "name": "update_task"
  }
}

Input Schema

Name	Required	Description
`type`	No	New type
`title`	No	New title — short and imperative, a few words. Not a sentence. Max 100 characters.
`areaId`	No	New area ID. Pass null to clear the task's area.
`status`	No	New status
`taskId`	Yes	The task ID or number (FB-360 or 360)
`context`	Yes	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."
`priority`	No	New priority
`projectId`	Yes	The project ID
`releaseId`	No	New release ID. Pass null to move the task to the Backlog (no release).
`assignedTo`	No	Replace assignees with this array of project member IDs; [] clears all
`description`	No	New description — 1–2 short plain-language sentences. Deeper technical detail belongs in agentContext, not here.
`agentContext`	No	Implementation notes: constraints, related files and prior decisions. Markdown supported. Changes are audited with before/after values.
`showOnRoadmap`	No	Whether the task should appear on the public Feedback Portal roadmap
`completionPolicy`	No	Required when marking Done with incomplete subtasks: complete them or explicitly override

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Beyond annotations, the description discloses that changes are audited with before/after values, that release/area names are resolved to real IDs, that notes do not assign placement, and that release descriptions may need review after task movement. These details materially improve the agent's ability to predict side effects. The behavior is consistent with destructiveHint=true and idempotentHint=true.

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 description is front-loaded with the core action and then covers conditional behavior in a logical sequence. Most sentences earn their place, though a few details duplicate schema descriptions, such as the null-to-Backlog and completionPolicy rules. It remains dense but readable for a complex 14-parameter mutation tool.

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 complex mutation tool with 14 parameters, no output schema, and rich annotations, the description covers the critical side effects and conditional requirements. It does not explicitly state that unspecified fields remain unchanged or describe permission requirements. Still, combined with the schema and annotations, it gives an agent enough to invoke the tool correctly.

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 parameter documentation is already strong. The description still adds meaning beyond the schema by explaining name resolution for release/area values and clarifying that notes do not assign placement. It repeats null semantics already present in the schema but adds useful operational context.

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 states a specific verb and resource: 'Update fields on an existing task.' It clearly implies mutation of an existing task rather than creation, deletion, or subtask editing. However, it does not explicitly differentiate from close siblings such as task_complete or task_edit_subtask, which also modify task state.

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 gives useful conditional guidance: verify with get_task, use completionPolicy when marking done with incomplete subtasks, and pass null to move to Backlog or clear an area. It also warns to check release descriptions after moving tasks into or out of a release. It stops short of explicitly naming alternatives like task_complete for status transitions.

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

All Frostbyte tools Inspect

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

Need Help?