next_question

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

With no annotations, the description carries the transparency burden. It discloses critical behaviors: reading aloud, returning only metadata ('never the text'), and the meaning of read_aloud=false. This goes beyond the basic action and helps the agent understand the tool's interaction model.

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 three sentences, front-loaded with the primary action, and every sentence adds value: action, return behavior, and usage advice. No filler or repetition.

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 that an output schema exists and the parameter schema is fully documented, the description covers the essential context: purpose, return type, and calibration guidance. It slightly lacks edge-case behavior (e.g., what if no next question), but this is minor for a tool of this complexity.

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 100% and the schema already provides rich semantics for both parameters (read_aloud explains its effect on grading, question_id explains when to jump). The description itself adds no additional parameter-level meaning, so the baseline of 3 applies.

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 and resource: 'Advance to the next question and read it aloud.' This clearly distinguishes it from siblings like repeat_question, and the phrase 'never the text' clarifies its scope.

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 provides clear context: 'Use the type to calibrate' gives actionable guidance after the call, and 'Use in candidate-led cases' explains when question_id should be used. However, it doesn't explicitly name when not to use this tool or contrast with alternatives like repeat_question.

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