What should happen now

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

Annotations already declare readOnly and non-destructive behavior. The description adds that it is idempotent and time-aware, and that it returns arguments for other tools, without conflicting with the annotations. It does not mention any side effects beyond read-only retrieval, which is consistent.

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?

The description is dense and well-structured, packing essential information into two sentences. It lists example tool calls, explains the return value, and gives usage instructions without redundancy or fluff.

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?

Given there is no output schema, the description adequately describes what is returned (phase and ordered checklist with reasons and arguments) and how to use it (execute and repeat). It also covers scheduling and idempotency, making it self-contained for an agent.

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 tool has zero parameters, so the baseline score applies. The description does not need to elaborate on parameters since none exist. The lack of parameters is fully covered by the input schema.

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 clearly states the tool returns the current phase and an ordered checklist of due tool calls, with explicit examples of actions (propose, send ballot, etc.). It also positions itself as the entry point ('START HERE'), distinguishing it from sibling tools that perform specific actions.

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 explicitly instructs to execute the returned calls and repeat until empty, and notes it is safe to call on a schedule due to idempotency and time-awareness. This gives unambiguous when-to-use guidance, including that it should be the first tool invoked.

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