Skip to main content
Glama
Sign In

Joe Speaking

by io.github.hubeiqiao
OverviewDiscussionsAdmin

IELTS/CELPIP practice and IELTS mock-test links

get_joe_speaking_practice_link
Read-onlyIdempotent

Returns verified links to IELTS Part 1, Part 2 and Part 3 practice, IELTS mock tests, CELPIP task practice and saved-recording retries in Joe Speaking. The app offers exam-timed practice, IELTS AI examiner follow-ups, recorded-audio assessment against Fluency and Coherence, Lexical Resource, Grammatical Range and Accuracy, and Pronunciation, and saved attempts for later review. CELPIP has task-specific formats and timing. Exact preparation links depend on availability; other results open an app or Simulator chooser for manual selection. Read-only lookup; recording, assessment and test start happen in Joe Speaking after the learner opens it. Use when the learner wants timed speaking practice, a mock test, a band-assessment entry, a retry, or help getting started. Speaking practice, recording, scoring and mock tests take place in Joe Speaking. Available fields include practiceOptions, destination, exactDestination and assistantInstruction. When onboarding is requested, also returns a howItWorks guide. The lookup does not start a microphone, record, score or charge. Joe Speaking saves practice completed in the app. Chat practice is not saved to Joe Speaking.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_joe_speaking_practice_link"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoExact Joe Speaking question or saved-practice URI previously returned by a tool.
examNoExplicit practice scope. With no value, verified source and available saved exam or goal determine the entry.
modeNoAn omitted mode returns all verified options available for the source: recording and, where available, mock or simulator options. Each explicit mode narrows the result: single_question to one-question recording, mock_test to an examiner mock, full_mock to a complete IELTS mock, and retry to a saved answer.
partNoIELTS part, when specified by the learner.
taskNoCELPIP task matching the selected question, from task1 through task8.
onboardingNoTrue adds the visual howItWorks guide for getting started, understanding app versus chat, no saved records, earlier chat-only practice, or finding a self-study entry. Established-user recommendations, question preparation and retries use the compact result without this guide.
recordingIdNoExact saved attempt ID within the referenced recording-practice session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / exam / description
      Previous value: -"Explicit practice scope; omit when unknown."New value: +"Explicit practice scope. With no value, verified source and available saved exam or goal determine the entry."
    • changedInput schema / properties / mode / description
      Previous value: -"Use mock_test for an examiner/mock request, full_mock for a complete mock, retry for a saved answer; otherwise single_question."New value: +"An omitted mode returns all verified options available for the source: recording and, where available, mock or simulator options. Each explicit mode narrows the result: single_question to one-question recording, mock_test to an examiner mock, full_mock to a complete IELTS mock, and retry to a saved answer."
    • changedInput schema / properties / onboarding / description
      Previous value: -"Set true only for how-to, just connected, app/chat difference, no saved records, earlier chat-only practice, or feeling lost / asking how to self-study IELTS speaking; returns the visual howItWorks guide. Omit for established-user recommendations, question prep and retries."New value: +"True adds the visual howItWorks guide for getting started, understanding app versus chat, no saved records, earlier chat-only practice, or finding a self-study entry. Established-user recommendations, question preparation and retries use the compact result without this guide."
    • changedInput schema / properties / ref / description
      Previous value: -"Exact Joe Speaking question or saved-practice URI already returned by a tool. Never guess an ID."New value: +"Exact Joe Speaking question or saved-practice URI previously returned by a tool."
    • changedInput schema / properties / task / description
      Previous value: -"CELPIP task; must agree with the returned question."New value: +"CELPIP task matching the selected question, from task1 through task8."
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real behavior: exact links depend on availability and may fall back to an app or Simulator chooser for manual selection, the lookup does not start a microphone, record, score or charge, and chat practice is not saved. This is substantive disclosure beyond the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The purpose is front-loaded, but the text is long and repeats itself: "Read-only lookup" duplicates the annotation, and "recording, assessment and test start happen in Joe Speaking" is effectively restated later as "Speaking practice, recording, scoring and mock tests take place in Joe Speaking." Several sentences could be merged without loss.

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

Completeness4/5

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

For a 7-parameter, zero-required lookup with no output schema, the description covers trigger conditions, fallback behavior, side-effect boundaries and the key result fields (practiceOptions, destination, exactDestination, assistantInstruction, howItWorks). It is close to complete; return-value shape is only sketched rather than fully explained, which keeps it at 4.

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 100%, so the enum semantics for exam, mode, part, task, onboarding and recordingId are already fully documented in the schema. The description adds little parameter-level meaning beyond general scope; the field names it lists (practiceOptions, destination, exactDestination, assistantInstruction) describe output, not inputs, so the baseline 3 is appropriate.

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

Purpose4/5

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

The opening sentence names a specific verb ("Returns verified links") and enumerates the resources: IELTS Part 1-3 practice, mock tests, CELPIP task practice and saved-recording retries. It clearly separates this lookup from the actual speaking/recording work, implicitly distinguishing it from open_joe_speaking, though it never names that sibling explicitly.

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?

"Use when the learner wants timed speaking practice, a mock test, a band-assessment entry, a retry, or help getting started" gives concrete triggering contexts, and the schema enums reinforce per-mode narrowing. There is no explicit when-not-to-use condition or named alternative sibling, so it stops short of a 5.

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

All Joe Speaking toolsInspect
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.

Resources