UK Data: Quiz questions

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: a 1-credit cost and the scope limitation that it does not report per-category question counts. Return shape is only implied via examples rather than stated directly.

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 tight sentences: the capability and its examples come first, then the scope caveat and cost. Every clause carries information an agent needs, with no redundant restatement of the name.

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?

For a zero-parameter list tool with no output schema, the description is sufficient: it discloses what is returned (category names with ids), the domain scope, the cost, and which sibling tools consume the output. No gaps remain that would cause a mis-invocation.

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 schema has zero parameters, so there is nothing to disambiguate and the baseline is 4. No parameter guidance is needed or missing.

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?

States a specific verb and resource (lists Open Trivia Database quiz categories) and gives concrete id/name examples (9 General Knowledge, 21 Sports), so an agent knows exactly what comes back. It is clearly distinct from the sibling trivia_questions, trivia_true_false, and trivia_question_count tools.

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 routes the agent: use this to plan rounds and pass a category to trivia_questions or trivia_true_false, and use trivia_question_count for per-category question totals. Both the when-to-use and the when-not-to-use alternatives are named.

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

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

The annotations already cover read-only, idempotent, and open-world behavior, so the bar is lower, but the description still adds useful meaning: counts cover only reviewed questions, and the API doesn't split them by question type. The mention of a credit cost also gives context beyond the annotations.

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 definition uses one front-loaded sentence that gives the core count behavior and difficulty split, then a clarifying sentence and short parentheticals. It is dense but purposeful, with no filler.

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?

There is no output schema, so the description usefully explains the shape of the result: counts by difficulty, with multiple-choice and true/false combined. It omits details such as return format or whether counts can be zero, but the definition is otherwise sufficient for a single-parameter query tool.

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 schema already documents the single category parameter fully, including accepted IDs and name examples. The description only implies category scoping ('one category') and adds no format or syntax details beyond the schema, so the baseline 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: it counts reviewed questions held in one category, split by easy/medium/hard. This is clearly distinguishable from siblings such as trivia_questions and trivia_true_false, which fetch questions rather than return counts.

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 gives a concrete use case: plan a quiz round without requesting more questions than exist, with the note that some categories hold only a few dozen hard questions. It doesn't explicitly name trivia_questions as the alternative for when you actually want the questions, but the context is still clear.

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

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

The description adds genuinely useful context beyond the annotations: 1-credit cost, Open Trivia Database provenance with CC BY-SA 4.0 licensing, English-language bias, possible stale answers, and non-curriculum alignment. However, "Questions are drawn at random each call" directly conflicts with the declared idempotentHint=true, since repeated identical calls will not return the same result.

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 core payload and option ordering are front-loaded in the first clause, and the caveats (randomness, language bias, dating) are properly subordinated at the end. It runs long as a single dense sentence-chain, and the licence parenthetical is more provenance than agent guidance, but nothing is truly wasted.

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?

There is no output schema, so the description must carry the return shape, and it does precisely: correct answer, three distractors, and four options in fixed A-D order with the correct letter flagged. Cost, randomness and source-quality limits are also disclosed, leaving nothing an agent needs in order to call it correctly.

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 already documents amount (1-50, default 10), category (id 9-32 or name) and difficulty (easy|medium|hard, default mix). The description only echoes the category examples and the "or mix" default behaviour, adding no syntax or format detail the schema lacks, so the baseline 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?

"Multiple-choice quiz questions, each with the correct answer, three wrong answers and the four options in a fixed A-D order" states a specific resource and returns shape, and "multiple-choice" separates it from trivia_true_false while the schema points to trivia_categories. An agent can pick it over its three trivia siblings without opening a schema.

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?

"Pick a category ... and difficulty, or mix" plus named domains ("pub quiz rounds, classroom quizzes and team events") give clear when-to-use context. It stops short of explicit exclusion routing such as "for true/false questions use trivia_true_false", so it is strong context rather than full alternative routing.

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

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

Adds genuinely useful behavior beyond the annotations: a 1-credit cost, random draw on every call, and the scarcity risk of narrow filters. However, 'Statements are drawn at random each call' sits awkwardly against idempotentHint=true, since repeating the same call will not return the same statements; the description and annotation pull in different directions. It also never says whether the answer is returned as a separate field or embedded, which matters for a quiz consumer.

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?

Front-loads what the tool returns and from where, then adds purpose, then the randomness/scarcity caveat, then cost. Every sentence carries information; the only mild padding is the CC BY-SA attribution, though that is defensible since license terms may need to be surfaced to users.

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?

For a zero-required-parameter read tool with a fully documented schema and no output schema, the description covers source, license, filtering axes, randomness, pool-size risk and cost. The one gap is the shape of a returned statement (fields present, whether the answer is separated), which an agent cannot infer from the schema alone.

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% and already documents amount (1-50, default 10), category (id 9-32 or name) and difficulty (easy|medium|hard, default mix), so the baseline is 3. The description adds only marginal semantic value by noting the default is 'mixed' and that narrow category+difficulty intersections shrink the pool, which is a useful interaction hint but not parameter-level detail beyond the 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?

States a specific resource and format ('True-or-false quiz statements with the correct answer') plus the source (Open Trivia Database) and the selection axes (category, difficulty, or mixed). The line 'the true/false bank is smaller than the multiple-choice one' implicitly but clearly separates it from the sibling trivia_questions tool, so an agent can pick the right one without opening a schema.

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?

Gives concrete use contexts ('quick rounds, icebreakers and classroom warm-ups') and a real usage caveat: narrow category plus difficulty combinations may return only a handful because the true/false bank is small. It stops short of naming an alternative tool (e.g. trivia_questions for multiple choice, trivia_question_count to check availability) or saying when not to use it, so it is clear but not exhaustive.

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