Skip to main content
Glama

APICK

by app.apick

LLM 채팅

llm_chat
Read-only

Send a chat request to a selected LLM model and receive the assistant reply. 선택한 LLM 모델에 대화를 보내고 assistant 응답을 받습니다. 서버는 대화 히스토리를 보관하지 않는 stateless 방식 — 매 호출마다 전체 히스토리를 messages 로 전송하고, 응답의 compacted_messages 를 다음 턴의 messages 로 그대로 재사용합니다. 사용 가능한 모델은 llm_models Tool로 조회합니다. 토큰 사용량에 비례해 포인트가 차감됩니다. [무료]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelYes모델 id (llm_models Tool로 조회 가능, 예: openai/gpt-oss-120b)
speedNo응답 속도/추론 깊이 — 'fast'(얕게, 빠름) | 'medium' | 'slow'(깊게, 느림). 한글 '빠름'|'중간'|'느림' 허용. 추론 특화 모델에서 효과가 큽니다
systemNosystem 프롬프트 (역할·페르소나·정책·배경지식). 미지정 시 기본 한국어 어시스턴트 프롬프트가 적용됩니다
compactNo히스토리 압축 옵션 { strategy: 'none'(기본) | 'sliding_window', window_pairs: 유지할 user/assistant 페어 수 (기본 10, 최소 1) }. 긴 대화의 input 토큰 누적 방지
contentNo단발 입력 — 사용자 메시지 한 건만 보내는 간편 형태. messages 와 둘 중 하나는 필수
messagesNoOpenAI 형식 [{role, content}] 배열. role 은 'system'|'user'|'assistant'. content 와 둘 중 하나는 필수, 동시 지정 시 messages 우선. 멀티턴 대화는 응답의 compacted_messages 를 다음 턴에 그대로 전송
max_tokensNo응답 최대 토큰. 미지정 시 모델 컨텍스트 기반 안전 상한으로 자동 설정, 상한 초과 지정 시 자동 조정
temperatureNo출력 다양성 0.0~2.0. 낮을수록 재현성, 높을수록 창의성 (미지정 시 모델 기본값)

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, but the description discloses significant behavioral traits: stateless conversation handling, the need to reuse compacted_messages for subsequent turns, and cost implications (point deduction based on token usage). These details go well beyond the annotations and inform correct usage without contradiction.

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 front-loaded with the core purpose, followed by distinct, non-redundant information about statelessness, model lookup, and cost. The Korean translation repeats the first sentence, which is acceptable for bilingual support but adds slight redundancy; still, every other sentence earns its place.

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?

For a tool with 8 parameters, nested objects, and no output schema, the description covers the essential context: purpose, stateless protocol, model discovery, cost, and how to handle multi-turn history. It does not detail the full return structure, but for a chat tool the response type (assistant reply) is clear; the compacted_messages mention bridges the gap.

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?

Input schema covers all 8 parameters with descriptions, so the baseline is 3. The description adds operational meaning by explaining the messages lifecycle (compacted_messages reuse), the distinction between content and messages, and model selection. This enriches parameter semantics beyond the schema.

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 opens with a specific verb+object: 'Send a chat request to a selected LLM model and receive the assistant reply.' This unambiguously identifies the tool's function and differentiates it from sibling tools like llm_models (which lists models) and text processing utilities.

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 gives clear operational guidance: emphasizes the stateless server, instructs to send full history via messages, and directs users to llm_models for model discovery. It lacks explicit exclusions or 'when not to use' but provides strong context for proper invocation.

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

All APICK toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

Most tools have clearly distinct purposes; even within families like identi_card1-5 vs identi_card_image1-5, the text-input vs image-input distinction is clear. However, the sheer number of tools and some near-synonyms (e.g., ocr_identi1 vs identi_card_image1) could cause occasional misselection, but descriptions mitigate this.

Naming Consistency3/5

Naming follows a loose verb-first pattern (check_, crawl_, download_, draw_, etc.) but includes significant deviations: bare nouns (bank_code, location, whois), numbered variants (identi_card1, identi_card_image1), and mixed prefixes (ocr_, identity_, etc.). The inconsistency is noticeable but still readable and predictable within functional clusters.

Tool Count3/5

80 tools is far above the typical 3-15, but the server is a broad API aggregator covering many independent domains (banking, ID verification, media conversion, search, LLM, etc.), so the high count is somewhat justified. Still, the sheer number makes the toolkit feel unwieldy and hard to navigate, placing it at the high end of acceptable.

Completeness4/5

Within its stated purpose as a general-purpose utility API, the toolset covers a wide array of common task families: identity document verification (text and image), OCR field extraction, media conversion, web/search, domain/IP lookup, and LLM chat. Most operations have both get and act variants (e.g., set/get watermark, parcel_tracking/auto), with few obvious dead ends for typical use cases.

Resources