Skip to main content
Glama

Agent Data Tools: Full list (every tool as its own definition)

Language detection: detect the language of a text

text_language
Read-only

Language detection for a text: the most likely language with its ISO 639-3 and 639-1 codes and English name, plus the next candidates with relative scores, using trigram statistics for 82 major languages (franc-min). Works best above about 20 characters; very short or mixed text returns und (undetermined). Local, no outside service. Use to route messages, pick a translation target or filter content by language. Example: text=Det här är en mening skriven på svenska om väder och resor.. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

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": {
      "text": "<text>"
    },
    "name": "text_language"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe text (up to 10,000 characters)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint=false, and destructiveHint=false, and the description reinforces this with "local, no outside service" and "reads or computes only and changes nothing." It adds genuinely new operational facts: per-call billing ($0.01 via x402 USDC or card key), 25 free calls, failed calls free, and that repeated identical calls are still charged — which explains the otherwise puzzling idempotentHint=false for a pure function. No contradiction with any annotation.

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?

Capability, limits, and output format are front-loaded in the first two sentences, with pricing and use cases after — a sensible ordering for scanning. The example ends with a doubled period ("resor..") and the billing sentence is dense, but no sentence is purely padding.

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 describe the return value, and it does so precisely: most likely language with both ISO codes and English name, plus ranked candidates with relative scores, and und for undetermined. Combined with the length limits, locality, and cost model, an agent has everything needed to call this correctly and interpret 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?

The single parameter has full schema coverage (description plus the 10,000-character cap), so the baseline is already met by structured data. The description still adds real meaning by telling the agent that results degrade below roughly 20 characters and that mixed-language input yields und, which is input-quality guidance the schema does not convey.

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?

"Language detection for a text" pairs a specific verb with a specific resource, and the description goes further by naming the engine (franc-min), the coverage (82 major languages), and the exact return shape (most likely language plus ISO 639-3/639-1 codes and ranked candidates). What it never does is differentiate itself from the sibling named language_detect, which an agent scanning the tool list would plausibly confuse it with.

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 concrete use cases — routing messages, picking a translation target, filtering content by language — which is a clearer usage signal than most definitions carry. The 20-character working threshold and the "short or mixed text returns und" condition are effectively when-not-to-expect-results guidance. It stops short of naming an alternative tool should be used instead for short strings.

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.