Skip to main content
Glama
Waypoint IEP Differentiation Server

Waypoint IEP Differentiation Server

by Maliik-B

scaffold_question

Generates scaffolded lesson questions calibrated to a student's reading level, with sentence starters, chunked sub-questions or fill-in-the-blank handouts for teacher or student use.

Instructions

Generate a scaffolded version of a specific lesson question calibrated to the student's reading level (Grade 3 iReady, Grade 2 informational text). Produces sentence starters, graphic organizers, chunked sub-questions, or fill-in-the-blank alternatives. All scaffolds use the actual lesson content (specific paragraphs, vocabulary, examples). Available levels: light/moderate/intensive. Supports 'teacher' mode (includes expected answer hints for the teacher's reference) and 'student' mode (clean handout without answers, ready to photocopy).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "question_id": "<question_id>"
    },
    "name": "scaffold_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoOutput mode. 'teacher' includes expected answer hints for the teacher's reference copy. 'student' produces a clean handout without answer hints, ready to photocopy and hand to the student.teacher
question_idYesThe question ID to scaffold (e.g., 'DR-1A', 'MC-1', 'SA-1', 'DISC-1'). Use 'all' to scaffold every question.
scaffolding_levelNoHow much scaffolding to provide. Light = paragraph hints. Moderate = sentence starters + chunked questions. Intensive = fill-in-the-blank with word banks.moderate

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses what is produced, that scaffolds are grounded in actual lesson content, how the teacher/student modes differ, and what each level yields. It stops short of saying whether output is returned inline or persisted, and says nothing about side effects or limits.

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?

Front-loaded with purpose and output types before the level/mode detail, and every sentence is on-topic. Minor waste in re-explaining teacher vs. student mode and the level tiers that the schema already defines.

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 3-parameter generation tool with no output schema and no annotations, the description covers inputs, output artifact types, content grounding, and mode differences well. The remaining gap is the shape of the returned result, which the agent must discover by calling.

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 coverage is 100%, so the schema already explains question_id, mode, and scaffolding_level in detail. The description's level and mode sentences largely restate the enum descriptions; its only real addition is the reading-level calibration context (Grade 3 iReady, Grade 2 informational text).

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?

States a specific verb+resource: 'Generate a scaffolded version of a specific lesson question,' and narrows it further with the calibration target and the four concrete artifact types (sentence starters, graphic organizers, chunked sub-questions, fill-in-the-blank). This clearly separates it from siblings like generate_lesson_modifications or generate_sub_card.

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

Usage Guidelines3/5

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

The description gives implied usage (scaffolding a specific question at a student's reading level) and enumerates levels and modes, but never says when to prefer this over generate_lesson_modifications or match_accommodations, nor any prerequisite or exclusion. The agent must infer routing from sibling names alone.

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