write_rotation_round

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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description earns credit by disclosing the concrete destruction: restart means 'nothing logged before now counts for it,' and the round's future date pins are cleared when replaced or stopped. The trailing openGym merge sentence is opaque and only loosely tied to this tool's actions, which keeps it from a 5. No auth/permission requirements are mentioned.

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?

Purpose is front-loaded and there is little filler, but the content is delivered as one dense run-on paragraph with no structure, and the final sentence about openGym merging settings and plans one setting/day at a time does not clearly earn its place in a description of round control.

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?

For a single-enum mutation tool with no output schema, the description covers actions, state effects, and persistence behavior, and annotations carry the safety profile. Remaining gaps are secondary: what happens to any in-progress session on stop, and what the call returns.

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?

Schema description coverage is 0% and the single 'action' parameter carries only a bare enum, so the description does all the work. It defines the observable behavior of every allowed value (start/restart/stop), which is exactly the compensation a low-coverage parameter needs.

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 opens with a specific verb+resource: 'Control the round of the app's own rotation,' and then enumerates the three operations (start/restart/stop). It implicitly separates the running 'round' from the rotation definition owned by the sibling write_rotation, but that distinction is never stated outright, so sibling differentiation is left to inference.

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?

Each action value is given a selection condition: 'start' applies when none is running, 'restart' when you want the loop over from the first routine today, 'stop' to end while keeping it saved. It also references write_schedule_mode ('"week" goes back to weekdays'), giving cross-tool context. It stops short of stating when NOT to use this tool versus write_rotation.

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