Fiveable for AP Students

Get multiple-choice practice questions

get_practice_questions

Read-onlyIdempotent

Returns original, course-specific multiple-choice practice questions. Free-text topics are matched against Fiveable's course map, so natural phrasing works. Omit topic to get balanced practice across the whole subject, with varied units, skills and stimulus formats. For history, science and language subjects this can return source-based sets — one stimulus with several questions off it — and stimulus images come back as viewable images. This is targeted or mixed practice, distinct from Fiveable's durable adaptive diagnostic.

Every question carries a Question id that supports a saved answer submission for student progress. The recentCorrect and recentAnswered inputs allow the tool to drop to easier question types when a student is missing questions, helping find where understanding breaks down. A returned question set consumes one full-content preview unless existing access covers this practice feature. Moderate cost — roughly 300 tokens per question, more when images are attached.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	Yes	"exam" requests Fiveable's balanced whole-course practice mix of units, skills and stimulus formats. "topic" drills one scope. "auto" picks exam when no topic is given.	auto
`tier`	No	The tier the student was just working at — pass back the tier from the previous result, along with recentCorrect / recentAnswered, so a student who is still missing comprehension questions drops to vocabulary rather than being handed comprehension again. On its own it pins the level: stimulus = source-based application, comprehension = does the student know the content, vocabulary = does the student know the terms.
`limit`	Yes	Exact maximum number of questions to return, including questions in a stimulus set.
`topic`	No	Free-text topic, e.g. "photosynthesis" or "the American Revolution". Matched against Fiveable course topics, then key terms. Omit for whole-subject mixed practice.
`intent`	No	Privacy-safe reason for the request. Use explain, quiz, notes, frq, or research; never send the student's raw prompt for analytics.
`unitId`	No	Exact unit id, public id, or slug from get_subject_outline. Use this for broad practice across a unit; do not substitute one topic id as a proxy for the entire unit.
`topicId`	No	Exact topic id from get_subject_outline, if known.
`subjectSlug`	Yes	Fiveable subject slug, e.g. "ap-bio". A course name such as "AP Biology" also resolves.
`recentCorrect`	No	How many of the student's recent answers were correct, for automatic tier adjustment.
`includeAnswers`	Yes	Defaults false so students can attempt questions before seeing the key. Set true only when the student explicitly asks for answers. Use check_practice_answer anonymously or submit_practice_answer when signed in.
`questionFormat`	Yes	"auto" matches what the subject's own practice UI leads with. "stimulus-set" requests source-based questions; "standalone" requests single questions with no shared source.	auto
`recentAnswered`	No	How many questions the student recently answered. Needs 3+ before the tier moves.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	No	Readable tool result text for clients that consume structured output.
`status`	Yes	Operation status: completed, pending, partial, failed, unavailable, or a domain-specific outcome.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 21, 2026

changedInput schema / properties / subjectSlug / description

Previous value: -"Fiveable subject slug, e.g. \"ap-bio\"."New value: +"Fiveable subject slug, e.g. \"ap-bio\". A course name such as \"AP Biology\" also resolves."

First observedSep 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already mark readOnly and idempotent, so the description's added detail about topic matching, source-based stimulus sets, viewable images, and consumption of one full-content preview is genuinely additive. It also discloses token cost and adaptive tier-dropping behavior, which an agent needs to predict side effects. No statement contradicts 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but organized: core behavior first, then source-set nuance, then progress/adaptive behavior, then cost. Every sentence adds information not present in the schema (token cost, preview consumption, image rendering). A little redundancy around 'targeted or mixed practice' is minor.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with an output schema, the description covers selection behavior, scoping, adaptive inputs, access/cost side effects, and answer submission integration. Missing items like exact return shape are handled by the output schema, so the description is effectively complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of properties, so baseline is 3, and the description adds real value on top: natural-language topic matching, tier/recentCorrect/recentAnswered behavior for dropping difficulty, and auto mode selecting exam when no topic is given. It also clarifies limit includes questions in a stimulus set, which is not obvious from the schema alone. This pushes above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description opens with 'Returns original, course-specific multiple-choice practice questions' — a specific verb and resource. It further clarifies what the tool is not ('distinct from Fiveable's durable adaptive diagnostic'), and the schema's mode/topic params reinforce targeted vs mixed practice. This separates it from siblings like get_diagnostic_results and get_frq.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent when to omit topic for whole-subject mixed practice and when topic drilling applies, and explicitly distances the tool from the adaptive diagnostic. It also routes answer checking to check_practice_answer or submit_practice_answer, though it doesn't name the diagnostic sibling as an alternative. That's clear use-context with a partial exclusion, not exhaustive when/when-not.

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

All Fiveable for AP Students tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.