Skip to main content
Glama

Intex Institute

Check against WCAG 2.1

check_accessibility

A LaTeX project in. Each WCAG 2.1 criterion that software can decide, with its verdict, and every place a person is still needed, by file and line. It never says compliant. 3 cents a page from the key's credit. Up to 24 MB for the project. A project that cannot be built costs nothing; the answer gives the file and line.

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": "check_accessibility"
  }
}

Input Schema

NameRequiredDescriptionDefault
mainNoThe path of the main .tex file. Needed only when the project has more than one.
filesNoThe project's text files by their path inside the project, each file's whole text: the .tex files, and any .bib, .bbl, .sty, .cls or .tikz of your own. Example: {"main.tex": "\\documentclass{article}...", "chapters/one.tex": "..."}.
archiveNoInstead of files: the whole project as one .zip or .tar.gz, base64-encoded.
binary_filesNoFigures and other binary files by path, each base64-encoded. PNG and JPEG are placed as they are; a PDF, EPS or SVG figure is answered with its name, to be saved as a PNG.

Output Schema

NameRequiredDescriptionDefault
pagesNoPages of the PDF the project makes: what is billed.
cost_centsNoWhat this call cost.
credit_centsNoThe credit left on the key's account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior5/5

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

Annotations are sparse and mostly say this is not read-only and not idempotent (consistent with spending credit), and the description goes well beyond them: it discloses per-page cost charged to the key's credit, a 24 MB project ceiling, that unbuildable projects are free, and that the tool 'never says compliant' so results must be read as per-criterion verdicts rather than a pass/fail. That is exactly the kind of behavioral context an agent needs before spending money on a call.

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?

Every sentence carries information — purpose, never-says-compliant caveat, cost, size limit, failure policy — with no filler. The clipped telegram style ('A LaTeX project in.') and the lack of a full opening sentence weaken front-loading and make the very first line slightly harder to parse.

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?

With an output schema present, the description need not spell out return values, and it still covers cost, limits, and failure behavior. The remaining gap is procedural guidance (sibling routing, key/auth expectations) rather than anything blocking a correct invocation.

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 parameters (main, files, archive, binary_files) are already well documented, including the files-vs-archive alternative and base64 handling. The description adds only the 24 MB project limit and the no-charge-on-failure rule; it does not add meaning about which input mode to prefer or how the main path interacts with the file map.

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 description conveys a specific resource (a LaTeX project) and a specific output (a verdict per WCAG 2.1 criterion that software can decide, plus human-review spots by file and line), which is enough to distinguish it from the build/count siblings. It never states the verb directly — 'A LaTeX project in' is a fragment that leans on the name and title 'Check against WCAG 2.1' to say what happens.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance: nothing about prerequisites such as a key, nor any routing against alternatives like make_tagged_pdf or make_web_page that an agent might confuse with an accessibility check. Operational facts (3 cents a page, 24 MB) are cost/size constraints, not usage guidance.

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.

Resources