Skip to main content
Glama

Talkhao

Look up a Chinese word

look_up_word
Read-onlyIdempotent

Find a Chinese word from its characters, its pinyin (with tone marks, tone numbers or none) or a meaning in English, Spanish, Indonesian, Thai or Vietnamese. Covers the 4,999 words of HSK 1-6. Answers with the word's pinyin, meaning, HSK level and HSK 3.0 band, the meaning and stroke count of each character, an example sentence where there is one, its sound and its Talkhao page, and up to three other words when the question fits more than one.

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": {
      "word": "<word>"
    },
    "name": "look_up_word"
  }
}

Input Schema

NameRequiredDescriptionDefault
wordYesJust the word to look up, not the whole question: characters (反馈), pinyin with tone marks, tone numbers or none (fǎnkuì, fan3kui4, fankui), or a meaning in English, Spanish, Indonesian, Thai or Vietnamese (feedback)

Output Schema

NameRequiredDescriptionDefault
wordNo
matchYesHow the word matched: hanzi, pinyin, gloss, sense, pinyin-toneless, ... ; empty when nothing did
queryYes
trailNoThe signed-in learner's own state for the word (B1c); only with a token, and only when one word was found
othersYesDid you mean: up to three other words
languageYesThe language the answer is in: en, es, id, th or vi
language_noteNoSet when the learner's locale has no translations
matched_languageNoSet when the word was found through its meaning in another language than English or the answer's: es, id, th or vi ("say" is Vietnamese for drunk)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, closed-world, non-destructive behavior, so the safety profile is covered. The description adds genuinely new behavioral context: the fixed 4,999-word HSK 1-6 corpus (a hard scope limit), the fallback of returning up to three alternative words on ambiguity, and the 'where there is one' caveat for example sentences. It does not cover the no-match case.

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?

Front-loaded with the core action and input modes, then a second block describing the answer payload. It is dense but every clause carries information; the only soft redundancy is re-listing the input modes that the schema already documents in full.

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?

An output schema exists, so the description need not spell out return fields, and it already expands them anyway. With one fully documented parameter, rich annotations, and a named corpus, the definition is close to self-sufficient; only the empty-result behavior is unstated.

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% and the single parameter's schema text already lists characters, the three pinyin notations with concrete examples, and the five meaning languages. The description restates the same enumeration without adding format rules, normalization behavior, or disambiguation priority. Baseline 3 applies.

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?

States a specific verb (find) and resource (a Chinese word) and immediately enumerates the three input routes - characters, pinyin in three notations, or a meaning in five languages - plus the lookup corpus (HSK 1-6). An agent knows exactly what class of query this tool answers without opening the schema.

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?

Clear context is given for what inputs qualify ('Find a Chinese word from its characters, its pinyin... or a meaning'), and the schema-adjacent note 'Just the word to look up, not the whole question' steers the agent away from passing raw user questions. However, no sibling tool is named and no explicit when-not condition is stated, so routing to hsk_words or stroke_data is left to inference.

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