Skip to main content
Glama

Preview SAT multiple-choice questions

preview_sat_questions
Read-only

Validates SAT multiple-choice questions, previews the Anki notes they would create, checks existing questions and deck status without writing to Anki, and returns a token for committing new cards.

Instructions

Validate SAT multiple-choice questions (exactly four choices A to D and one answer letter) and show the Anki notes they would create, with all text HTML-escaped. Reports which questions already exist in Anki, matched by tag, and whether the deck exists. If the deck is missing, says that commit_sat_preview will create it. Writes nothing to Anki. Returns a previewToken that expires in 10 minutes and works only in this server process. Pass it to commit_sat_preview to add the new questions.

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": {
      "deck": "<deck>",
      "questions": "<questions>"
    },
    "name": "preview_sat_questions"
  }
}

Input Schema

NameRequiredDescriptionDefault
deckYesDeck for the notes. If the deck is missing, commit_sat_preview creates it when at least one question is new.
questionsYesOne to fifty SAT multiple-choice questions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

The annotations already declare readOnlyHint=true and destructiveHint=false. The description goes well beyond that by saying no writes occur, matching is by tag, deck existence is reported, the previewToken expires after 10 minutes, and it works only in this server process. The process-local, expiring token is exactly the kind of constraint an agent cannot infer from the schema, and it agrees with idempotentHint=false.

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

Conciseness5/5

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

Roughly six short sentences, front-loaded with purpose, then behavior, then next steps. There is no filler, and every sentence carries independent information (validation, escaping, dedupe, deck check, token lifecycle).

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?

There is no output schema, so the description must cover return values, and it does: the Anki note previews, existence flags, deck status, and the previewToken with its lifetime. It is complete enough for an agent to call the tool and know what to do with the result.

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 description coverage is 100%, so the baseline is 3. The description adds real meaning by saying that text is HTML-escaped and that existing questions are matched by tag, which explains how the questions array is interpreted against Anki state and how the deck name is used when the deck is missing.

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 opens with a specific verb and resource: validate SAT multiple-choice questions and show the Anki notes they would create. It scopes the work precisely (four choices A-D, one answer letter, HTML-escaped text) and separates itself from commit_sat_preview, which is the tool that actually writes.

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 gives a clear routing rule for the next step: pass the returned previewToken to commit_sat_preview to add the new questions, and states that this tool writes nothing to Anki. It does not explicitly compare itself with the other siblings (preview_sat_quiz, export_sat_tsv, check_deck), but the preview-then-commit flow is unambiguous.

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