Skip to main content
Glama

Tolca: business verification (KYB)

homework-check

homework_check
Read-onlyIdempotent

Can this homework be done by an AI? For teachers and schools: paste an assignment (or a public PDF URL) and get an overall AI-completion risk 0-100, a per-question breakdown (risk, why, concrete fix to make it AI-resistant) and general tips. No student data. Input: text or url, optional grade, subject, lang fr|en. / Ce devoir peut-il être fait par une IA? Score par question et corrections concrètes pour l'enseignant. Costs $0.25 USDC per call (x402 v2, Base or Solana). Send the HTTP header PAYMENT-SIGNATURE with your x402 payment, or call POST https://tolca.tonbot.ca/v1/homework-check with an x402 client.

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": "homework_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoPublic URL of the assignment (PDF or page)
langNoLanguage of the report: fr or en
textNoAssignment text
gradeNoGrade level, e.g. secondaire 3
subjectNoSchool subject, e.g. math or history

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / lang / description
      Added value: +"Language of the report: fr or en"
    • addedInput schema / properties / subject / description
      Added value: +"School subject, e.g. math or history"
  2. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the description's real duty is the parts annotations cannot express: it does that well by stating the $0.25 USDC per-call cost, the x402 v2 payment scheme, the PAYMENT-SIGNATURE header and the endpoint. However, it omits failure behavior (what happens on an unpaid call, rate limits, timeouts, or handling of unreachable URLs), which matters for a paid open-world fetch.

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?

It is front-loaded with the core question, audience and outputs before inputs, costs and payment mechanics, so an agent gets the essentials immediately. The one wasted element is the French restatement of the same purpose, which duplicates meaning for most callers and lengthens the definition without adding selection signal.

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?

With no output schema, the description usefully specifies the return shape (overall 0-100 risk, per-question risk/why/fix, general tips) and the payment handshake, so an agent knows what it will get and what it must send. The remaining gaps are the zero-required-parameter ambiguity (text vs url) and missing error/no-payment behavior, which leave the operational contract slightly under-specified.

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% (url, text, lang enum, grade, subject all documented), so the baseline is 3. The description only restates the parameter list and hints that text and url are alternatives ('text or url'), without clarifying whether both may be supplied together or what happens if neither is given – especially relevant since zero parameters are marked required.

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 names a concrete question the tool answers ('Can this homework be done by an AI?'), the audience (teachers and schools), the input modes (assignment text or public PDF URL) and the exact outputs (0-100 risk, per-question breakdown, fixes, tips). Nothing in the sibling list (extract, summarize, company_enrich, sanctions_check, etc.) overlaps with this grading/risk-analysis resource, so an agent can pick it unambiguously.

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 tells the agent the situation for use (a teacher wants to know if an assignment is AI-completable) and one clear constraint ('No student data'), plus the accepted input forms. It stops short of naming when NOT to use it or which sibling to pick for adjacent tasks such as extracting text from a PDF, which would be a natural exclusion given extract_url exists.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.