Frostbyte

create_task

Create a new task in a project. When asked to add a bug, feature or task, create it directly after checking list_tasks for duplicates. Resolve a named release with list_releases and a named area with list_areas; pass their real releaseId and areaId fields, then verify with get_task. Notes do not assign placement. The request authorizes that assignment; ask only if the named target is missing or ambiguous. Explicit Backlog uses releaseId null; omission uses the active release. Signal-derived work uses null unless the user selects a release. After placing work in 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>",
      "title": "<title>",
      "context": "<context>"
    },
    "name": "create_task"
  }
}

Input Schema

Name	Required	Description
`type`	No	Task type (default: feature)
`title`	Yes	Short imperative task title — a few words (e.g. 'Add password reset'). Not a sentence. Max 100 characters; put detail in the description.
`areaId`	No	Area ID to assign the task to
`status`	No	Task status (default: todo)
`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	Task priority
`projectId`	Yes	The project ID
`releaseId`	No	Release ID to assign the task to. Pass null for the Backlog (no release); omit to use the active release.
`assignedTo`	No	Array of project member IDs to assign; [] leaves the task unassigned
`description`	No	Brief plain-language description — 1–2 short sentences on what and why. Deeper technical detail belongs in agentContext, not here.
`agentContext`	No	Implementation notes for the agent — constraints, related files, prior decisions. Markdown supported. Free-form prose with real depth, not a how-to. This is where technical detail goes, not the description.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare a non-destructive, non-idempotent, open-world write, so the description only needs to add context — and it does: it discloses the authorization stance (the request itself authorizes assignment), the mandatory duplicate-check behavior, and a post-placement check that the release description still matches scope. It doesn't say what the tool returns or what happens if creation fails, which caps it below 5.

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?

Purpose is front-loaded and most sentences carry distinct operational content. However, several sentences are compressed to the point of ambiguity — "The request authorizes that assignment" leaves the referent of "that assignment" implicit, and the release/Backlog rules are stated across three separate fragments that could be consolidated.

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, no-output-schema write tool, the description covers the risky parts well: placement into releases/areas, the ask-vs-proceed boundary, and duplicate prevention. It is thin on the lower-stakes params (status, priority, assignedTo) and never says what a successful call returns, though the schema descriptions do cover those fields.

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 the baseline is 3 and the description mostly restates what releaseId and areaId already document (null means Backlog, omission means active release). It does add genuinely new meaning for two parameters: "Notes do not assign placement" clarifies that description/agentContext text is not used for assignment, and the signal-derived-null rule scopes releaseId behavior beyond the schema wording.

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?

"Create a new task in a project" states a specific verb and resource, and the surrounding workflow text (duplicate check, release/area resolution) makes clear this is the creation path versus update_task, create_release, or create_area. An agent can identify the tool's job without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names prerequisites (check list_tasks for duplicates first), alternatives to call for name resolution (list_releases, list_areas), a follow-up verification step (get_task), and an explicit decision rule for when to ask the user versus proceed ("ask only if the named target is missing or ambiguous"). This is about as close to a routing policy as a description gets.

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?