detect_languageDetect the source language of a piece of text. Returns ranked language candidates with confidence.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to analyze |
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text that was analyzed | |
| candidates | Yes | Ranked language candidates with confidence scores |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "text": "Bonjour, comment allez-vous?"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "candidates": {
+ "description": "Ranked language candidates with confidence scores",
+ "items": {
+ "properties": {
+ "confidence": {
+ "description": "Confidence score for this language",
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "language": {
+ "description": "Detected language code",
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "text": {
+ "description": "Text that was analyzed",
+ "type": "string"
+ }
+ },
+ "required": [
+ "text",
+ "candidates"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds that it returns ranked language candidates with confidence, which is useful behavioral information beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences, front-loaded with the core purpose and immediately followed by the key output detail. Every word earns its place with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with an output schema and strong annotations, the description covers the essential what and return behavior. It could mention use cases but is not incomplete given the available structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with 'Text to analyze' for the text parameter. The description adds no additional parameter details such as length limits or encoding, so it reaches the baseline but does not exceed it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool detects the source language of text, using a specific verb and resource. It distinguishes itself from sibling tools like translate and list_languages, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives such as translate or list_languages. The description simply states what it does without any contextual or exclusionary notes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions to the same underlying Pipeworx catalog, and the five polymarket_* tools all analyze prediction-market opportunities and edge. While the individual descriptions are detailed, an agent could easily select the wrong tool without deep reading, particularly between ask_pipeworx and its beta/variant versions.
The naming style is a mixture of imperative verb phrases (translate, validate_claim, forget, generate_llms_txt), noun phrases (entity_profile, recent_alerts, polymarket_arbitrage), and brand-prefixed nouns (ask_pipeworx, pipeworx_trending, bet_research). While all names are lowercase with underscores, there is no consistent verb_noun or domain-prefix convention across the toolset, making the API feel grab-bag rather than designed.
The server is named 'Libretranslate' — a translation service that needs only translate, detect_language, and list_languages — yet it exposes 34 tools spanning data research, prediction markets, memory storage, subscriptions, dependency scanning, AI-visibility probing, and llms.txt generation. This is an extreme scope mismatch: the overwhelming majority of tools serve completely unrelated functions that have nothing to do with the server's apparent purpose.
If judged purely as a translation server, the core surface is present but thin: translate, detect_language, and list_languages cover basic use, though there are no batch, format, or language-details options. If judged as the broader heterogeneous toolset, the domain is incoherent — no single workstream is fully covered, and the unrelated tools (Polymarket betting, Pipeworx research, memory, subscriptions) create a muddled surface with obvious gaps in any single stated purpose.