Skip to main content
Glama

analyze_morphology

Analyze text morphology: tokenize, lemmatize, and tag parts of speech with UDPipe 2. Supports 961 language models for full-text search, filtering by word type, and passive voice detection.

Instructions

Tokenizuje, lemmatizuje a označuje slovní druhy pomocí UDPipe 2.

Pro každý token vrací **lemma** (základní tvar), **UPOS** (universal POS tag),
**morphological features** (pád, rod, číslo, čas...) a volitelně závislostní
parse (head + deprel) nebo character ranges (offsety do originálu).

UDPipe 2 podporuje **961 modelů** pro téměř všechny jazyky světa.
Auto-detect (default) rozezná: czech, slovak, ukrainian, russian, polish,
german, english, french (via heuristics).

Hodí se pro:
- Fulltextové vyhledávání v právních textech (lemma "soud" matchuje "soudu/soudem/soudy")
- Filtrování podle slovních druhů (jen substantiva, jen verba)
- Detekce pasivních konstrukcí (Voice=Pass)
- Vícejazyčné dokumenty (UA legal aid, EN smlouvy, DE Klage…)

Args:
    text: Vstupní text.
    model: UDPipe model alias. ``auto`` (default) detekuje jazyk podle markerů.
        Explicit: ``czech``, ``slovak``, ``english``, ``ukrainian``, ``russian``,
        ``polish``, ``german``, ``french``, atd. — 961 modelů celkem.
    include_parse: True = vrátí závislostní parse (head, deprel).
    include_ranges: True = vrátí ``token_range`` (char offsets do originálu).
        Užitečné pro inline highlighting nebo mapování token → text position.

Returns:
    ``sentences``, ``model``, ``token_count``, ``sentence_count``,
    ``detected_language`` (jen u auto).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
modelNoauto
include_parseNo
include_rangesNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

No annotations present, so description fully handles transparency. Discloses UDPipe 2 usage, 961 model support, auto-detect language list, and behavior of optional parameters (include_parse, include_ranges) with practical examples.

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?

Well-structured with bullet points and clear sections. Slightly lengthy due to language list, but overall concise and front-loaded with core purpose.

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?

Given presence of output schema, description need not detail return values. Covers input, use cases, and optional outputs adequately. Mentions output fields (sentences, model, token_count, etc.) for agent to infer structure.

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 coverage 0% requires description to explain parameters. Description explains 'text', 'model' (with defaults and examples), and both boolean flags with usage context. Lacks constraints (e.g., text length), but otherwise sufficient.

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?

Description clearly states tool performs tokenization, lemmatization, and POS tagging using UDPipe 2. Lists specific output fields (lemma, UPOS, morphological features, optional parse, ranges). Distinguishes from sibling tools like extract_entities and translate_text by focusing on morphological analysis.

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?

Provides explicit use cases (fulltext search, POS filtering, passive detection, multilingual documents) and mentions language auto-detection. Does not explicitly state when not to use, but the use cases are clear and differentiate from siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Buggy1111/anonymize-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server