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.

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.

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.

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.

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.

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.