Skip to main content
Glama
ALOC Model Context Protocol (MCP) Server

ALOC Model Context Protocol (MCP) Server

Official
by MaSSTeck

aloc_generate_assessment

Assemble a psychometrically balanced exam paper from syllabus presets or custom Bloom distributions, topics, and seeds to support reproducible assessments.

Instructions

Assemble a psychometrically balanced examination paper based on syllabus presets (JAMB 40, WAEC 50, Micro 10) or custom Bloom difficulty distributions, topics, and seeds. Consumes 5 ALOC credits.

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": {
      "subject": "<subject>",
      "examType": "<examType>"
    },
    "name": "aloc_generate_assessment"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoDeterministic seed for reproducible student batches
countNoNumber of questions (max 60, default 40)
presetNoStandard syllabus preset
topicsNoSpecific topics to cover in the assessment
subjectYesSubject name (e.g. 'mathematics', 'physics', 'english')
examTypeYesTarget African examination body
contentSourceNoContent provenance filter. Defaults to historical past questions; pass synthetic or all to explicitly include AI-generated questions.historical
shuffleOptionsNoWhether to randomize distractor option keys (anti-cheating)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.13

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose the significant cost signal ('Consumes 5 ALOC credits'), which is genuinely useful behavior beyond the schema. It says nothing about whether the generated paper is persisted, whether it must be paired with aloc_create_assessment_session to be usable, or about rate limiting and failure modes on insufficient credits.

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?

Two sentences, no filler, with the generation semantics front-loaded and the credit cost isolated at the end. Minor cost for unglossed jargon ('psychometrically balanced', 'Bloom difficulty distributions') that an agent cannot map onto any input field.

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

Completeness3/5

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

For an eight-parameter generative tool with no annotations and no output schema, the description should say what comes back (question objects, paper structure, an ID for a follow-up session). The credit cost is a valuable addition, but the post-generation workflow and return shape are left unstated.

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 documents all eight parameters and the enum values, making 3 the baseline. The description adds little beyond restating the preset concept, and it references 'custom Bloom difficulty distributions' even though the schema exposes no Bloom/difficulty parameter, which slightly muddies rather than clarifies parameter meaning.

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?

Uses a specific verb ('assemble') and resource ('examination paper') and names the concrete inputs that shape it (syllabus presets, Bloom distributions, topics, seeds). It does not, however, differentiate itself from the sibling aloc_create_assessment_session, leaving the generate-vs-create boundary implicit.

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?

Usage context is implied by the preset examples (JAMB 40, WAEC 50, Micro 10) and the alternative 'custom' path, so an agent can infer when a preset versus custom call is appropriate. There is no explicit statement of when to prefer aloc_create_assessment_session or aloc_search_questions, and no prerequisites or exclusions are given.

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