Stride — AI software delivery platform

Transition sprint

stride.transition_sprint

DestructiveIdempotent

Transition a sprint to a new status: ACTIVE (start a PLANNING sprint), COMPLETED (close an ACTIVE sprint; incomplete stories return to backlog), or CANCELLED. Only ONE sprint per project can be ACTIVE: starting a second returns SPRINT_ALREADY_ACTIVE naming the active one — complete or cancel it first (stride.list_sprints shows statuses). A sprint already in the requested state returns SPRINT_ALREADY_IN_STATE (with requestedState) and changes nothing — distinct from SPRINT_ALREADY_ACTIVE, which means a DIFFERENT sprint holds the slot. Illegal transitions return isError with the legal next states. Conflict-guarded against concurrent human edits (pass force:true, after re-reading with get_sprint, to override — the override is audit-logged).

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": {
      "sprintId": "<sprintId>",
      "to": "<to>"
    },
    "name": "stride.transition_sprint"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	Target status.
`force`	No	Required after a HUMAN_EDIT_AFTER_AGENT_SYNC conflict — re-reading with get_sprint does not clear it. Re-read first and account for the human's edit; overwrite it only with the human's explicit approval — the override is audit-logged.
`sprintId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 24, 2026

TDQS

A5/5.0

Behavior5/5

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

Beyond the annotations, it discloses the SPRINT_ALREADY_ACTIVE vs SPRINT_ALREADY_IN_STATE distinction, the incomplete-story backlog effect, illegal-transition isError responses, conflict guarding against human edits, and audit logging. This is rich operational context for a destructive mutation.

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?

It is a single dense paragraph front-loaded with transition states and effects, followed by error semantics and conflict handling. No sentence is filler; each adds operational value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still covers response semantics (error codes, isError), side effects (stories to backlog), and conflict recovery. That is complete for a three-parameter destructive tool.

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?

The schema documents the enum for 'to' and the force parameter, and the description adds lifecycle meaning per status (ACTIVE starts PLANNING, COMPLETED returns incomplete stories) and clarifies force is required only after HUMAN_EDIT_AFTER_AGENT_SYNC and must be preceded by get_sprint. The only undocumented parameter, sprintId, is self-evident.

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 states a specific verb ('Transition') and resource ('sprint'), then enumerates exactly the three target statuses and their lifecycle meanings. Its scope is clearly limited to status changes, which distinguishes it from general update operations even though update_sprint is not named.

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 explains when each transition applies (start PLANNING, close ACTIVE, cancel), what happens to incomplete stories, and points to stride.list_sprints for status checks and get_sprint for conflict re-reads. Error conditions and the force override path are also explicitly described.

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

All Stride — AI software delivery platform 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.