Create a poll

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

Discloses that the poll id is stored in a variable and that end_poll targets the last poll. Adds context beyond annotations (openWorldHint). No contradictions.

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, no fluff. Front-loaded with the main action. Every sentence adds 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?

Covers the main behavioral side effect (variable). Lacks details on failure modes or concurrent poll handling, but sufficient given the simple interface and annotations.

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 provides full descriptions for all 3 parameters (100% coverage). Description adds minimal extra value beyond mentioning the variable side effect. Baseline score applied.

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 poll', specifies the verb and resource. Distinguishes itself from sibling tools like create_prediction and end_poll by noting how the poll id is stored and used.

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?

Explicitly states 'Only works while live on Twitch', advising when to use. Does not mention when not to use or compare with alternatives beyond the implicit sibling list.

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