Skip to main content
Glama

extract_entities

Extract named entities from text in 35+ languages. Automatically detects language or selects Czech or multilingual model to identify persons, organizations, locations, and more.

Instructions

Rozpozná pojmenované entity pomocí NameTag 3 — CZ i 30+ dalších jazyků.

Pro **češtinu** používá bohatý CNEC 2.0 tagset (osoba/firma/instituce/
PSČ/telefon/datum/…). Pro ostatní jazyky (SK, EN, DE, FR, IT, ES, PT,
NL, PL, HU, UK, RU, RO, SL, BG, EL, HR, SR, FI, LT, LV, ET, DA, SV,
NO, ZH, AR, TR, VI, HI a další) přepne na multilingvální UNER model
s tagsetem PER/ORG/LOC.

Args:
    text: Vstupní text (UTF-8).
    model: ``auto`` (default) — automatická detekce CZ vs non-CZ.
        ``czech`` vynutí CNEC 2.0 (bohatý CZ tagset). ``multilingual``
        vynutí UNER PER/ORG/LOC pro non-CZ. Lze zadat i plné jméno
        modelu (např. ``nametag3-multilingual-onto-250203``).
    fix_romance: Default True. Pro PT/ES texty oprava typického
        UNER bugu, kdy se "X de Place" zaeviduje celé jako PER —
        wrapper rozdělí na PER + LOC a generuje warning.
    include_xml: Default ``False``. Inline XML s ``<ne type="...">`` tagy
        pro HTML highlighting (extra API call).
    include_vertical: Default ``False``. Tabulkový formát ``id\ttype\ttext``
        (extra API call).

Returns:
    ``entities`` (list s ``type``, ``label``, ``text``, ``tokens``,
    ``nested``), ``model``, ``count``, ``warnings``,
    ``detected_language`` (jen u ``auto``),
    ``xml`` (jen pokud ``include_xml``),
    ``vertical`` (jen pokud ``include_vertical``).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
modelNoauto
fix_romanceNo
include_xmlNo
include_verticalNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

No annotations are provided, so the description carries full burden. It discloses that include_xml and include_vertical cause extra API calls, and fix_romance generates warnings. It does not mention rate limits or auth, but the behavioral traits are adequately described.

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?

The description is well-structured with an overview, parameter details, and return values. It is informative without being overly verbose, though a slightly more streamlined presentation could improve conciseness.

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 the complexity (5 parameters, 1 required, output schema present), the description covers all parameters and return values comprehensively. It also notes extra API calls for certain options, ensuring the agent has sufficient context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description fully explains each parameter: text, model (with values and defaults), fix_romance (function and default), include_xml, include_vertical. It provides concrete details beyond the schema, such as model name examples and the effect of fix_romance.

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 clearly states it recognizes named entities using NameTag 3, supporting Czech with a rich tagset and over 30 other languages with a multilingual model. It distinguishes itself from sibling tools like anonymize or correct_text by focusing specifically on entity extraction.

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?

The description explains when to use different model options (auto, czech, multilingual) and mentions fix_romance for specific languages. However, it does not explicitly state when not to use this tool or compare it to alternatives, leaving some ambiguity.

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