run_exam_question_loop

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

With no annotations, the description carries the full disclosure burden and does a solid job: it enumerates five stop conditions, a 40-second time budget, resumability, cache-first behavior with current-model fallback, and critically states 'Never finally submits' — a meaningful safety guarantee for a mutation-ish loop. It omits auth/session prerequisites and what state the page must be in before calling.

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 lead sentence is front-loaded with verb, resource, and mechanism, followed by a compact stop-condition list and one line on cache behavior. Slight redundancy between 'Stops on an unknown answer' and 'cache misses require current-model review', but overall tight.

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?

An output schema exists so return shape needn't be explained, and the description adequately covers loop control and safety. However, for a multi-step driver tool with zero annotation coverage and zero parameter documentation, it should say what run_id refers to, how max_steps bounds the loop, and what the page must be set up as first.

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 description never mentions either parameter. 'Call again to continue' hints that a run identifier persists across calls, but max_steps (default 10) and run_id's meaning/origin are left entirely undocumented in both schema and prose.

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 names a specific verb and resource — 'Answer and save reviewed questions one at a time' — and adds the mechanism ('using the page's own Next action'), which anchors it as an iterative driver rather than a single read or save. It does not explicitly differentiate itself from near siblings like save_owned_exam_answer or exam_loop_progress, so an agent must infer the boundary.

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 states the termination conditions and that calling again continues, which is useful operational guidance, but never says when to prefer this loop over single-shot siblings (save_owned_exam_answer, read_current_exam_question) or what preconditions must hold (questions already reviewed/planned). Usage is implied rather than prescribed.

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