Create a prediction

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

Discloses caching behavior: 'The prediction id and outcomes are cached so end_prediction can resolve it by outcome title.' Annotations already indicate openWorldHint=true (side effects expected) and readOnlyHint=false (mutation). The description adds specific behavioral context beyond annotations without contradiction.

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?

Two sentences, zero wasted words. The most important information (purpose and key constraint) is front-loaded.

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?

Covers purpose, caching, and live-only condition. No output schema exists, so description could mention return format or error handling, but not strictly necessary for a creation tool. Slightly incomplete regarding what happens if not live, but adequate for the complexity level.

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 coverage is 100% with good parameter descriptions. The tool description adds no additional meaning beyond what the schema provides. Baseline of 3 is appropriate as the schema does the heavy lifting.

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?

Clearly states 'Start a Twitch channel-points prediction.' The verb 'start' and resource 'prediction' are specific. Differentiates from sibling tools like create_poll and end_prediction by explicitly referencing the caching mechanism for end_prediction resolution.

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?

States 'Only works while live on Twitch,' which is a crucial precondition. This tells the agent when the tool is valid to use. However, it does not explicitly mention when not to use it or suggest alternatives (e.g., if offline, use something else).

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