Fiveable for AP Students

Score an uploaded or pasted FRQ

score_external_frq_response

Idempotent

Scores a student's existing FRQ even when it did not come from Fiveable. If the student attached photos, the host AI must first transcribe the prompt and response, show the transcription for confirmation, then call this tool. Optional prompt images preserve graphs or artwork that text alone cannot represent. Fiveable scores it on the AP rubric for its exact question type, out of that type's AP point total. Requires sign-in; one scoring preview is included without a plan, with further scoring available to eligible accounts. The attempt is saved to the student's Fiveable progress. Returns a pending scoring job; poll get_scoring_result. Reuse requestId for retries.

Input Schema

TableJSON Schema

Name	Required	Description
`intent`	No	Privacy-safe reason for the request. Use explain, quiz, notes, frq, or research; never send the student's raw prompt for analytics.
`frqType`	Yes	The exact AP question type as Fiveable names it, e.g. "Document-Based Question (DBQ)". If it doesn't match, the tool lists this subject's types.
`requestId`	No	Stable unique request ID. Reuse it only for retries of the same submission; a new response needs a new ID.
`promptText`	Yes	Verified transcription or pasted text of the complete prompt.
`promptLabel`	No	Short label shown in attempt history.
`subjectSlug`	Yes	Fiveable subject slug, e.g. "ap-bio".
`promptImages`	No	Optional original prompt images for diagrams, graphs, maps, or artwork.
`partResponses`	Yes
`responseImages`	No	Optional response images that must be evaluated visually, such as a student-drawn graph.
`transcriptionConfirmed`	Yes	Must be true only after the student confirms the transcribed prompt and response text.

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 25, 2026
- changedInput schema / properties / requestId / pattern
```
Previous value: -"^[A-Za-z0-9_-]{8,128}$"New value: +"^[\\w-]{8,128}$"
```

Changed4 schema fields changedSep 25, 2026

changedInput schema / properties / frqType / description

Previous value: -"Response format, e.g. \"DBQ\", \"LEQ\", or \"Free Response\"."New value: +"The exact AP question type as Fiveable names it, e.g. \"Document-Based Question (DBQ)\". If it doesn't match, the tool lists this subject's types."

addedInput schema / properties / frqType / maxLength
```
Added value: +120
```

removedInput schema / properties / totalPoints

Removed value: -{
-  "description": "Maximum points for the response.",
-  "maximum": 50,
-  "minimum": 1,
-  "type": "integer"
-}

changedInput schema / required

Previous value: -[
-  "subjectSlug",
-  "frqType",
-  "promptText",
-  "transcriptionConfirmed",
-  "totalPoints",
-  "partResponses"
-]New value: +[
+  "subjectSlug",
+  "frqType",
+  "promptText",
+  "transcriptionConfirmed",
+  "partResponses"
+]

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 only indicate readOnlyHint false, idempotentHint true, etc. The description adds substantial behavior: requires sign-in, one free preview, saves attempt to progress, returns a pending job, and mandates polling. No contradiction with annotations; these are valuable beyond what annotations convey.

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 dense but well-structured, front-loading the core purpose before covering photo handling, scoring rubric, auth, polling, and retries. Every sentence adds necessary context, though it is slightly longer than necessary for a simple tool.

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 complex tool with 10 parameters and a required workflow, the description covers all critical operational aspects: external FRQ handling, image transcription, authentication, output as a pending job, polling, and retry semantics. With an output schema present, the return format is already defined, so nothing essential is missing.

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

Parameters3/5

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

Schema description coverage is 90%, so most parameters are already documented. The description adds minimal new meaning—mainly that promptImages preserve graphs/artwork, and reiterates the transcription confirmation workflow already in the schema. It does not significantly compensate for the remaining 10%.

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?

The description clearly states the tool scores a student's existing FRQ even when it did not come from Fiveable, using a specific verb and resource. It explicitly differentiates from the sibling tool score_frq_response by scoping to external FRQs, making the purpose unambiguous.

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

Usage Guidelines5/5

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

Provides explicit usage guidance: use this when the FRQ is external, and includes a detailed workflow for handling photos (transcribe, confirm, then call). It also instructs to poll get_scoring_result and reuse requestId for retries, covering when and how to use it effectively.

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.