image_edit원본 이미지와 편집 지시로 이미지 한 장을 편집하고 이미지 콘텐츠로 반환합니다. 장당 25포인트입니다. [이미지당 25포인트]
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | 표준 출력 크기, 기본 1024x1024 | |
| prompt | Yes | 편집 지시, 최대 28,000자 | |
| image_url | Yes | 원본 이미지 — 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg, image/webp) (최대 50MB) | |
| background | No | 배경 방식 | |
| output_format | No | 출력 포맷 | |
| idempotency_key | No | 같은 요청의 재전송으로 인한 중복 생성·과금을 막는 고유 키 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds useful behavioral context beyond the annotations: it advertises the cost (25 points per image) and clarifies the output is returned as image content. Annotations already cover idempotency and non-destructive behavior, so the description's additional pricing and return-type disclosure is meaningful and non-redundant.
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 short and front-loaded with the core purpose, and the cost sentence is useful. However, the pricing information is repeated unnecessarily ('장당 25포인트입니다' and '[이미지당 25포인트]'), introducing minor 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 tool with six parameters, a complete schema, and annotations covering idempotency and safety, the description provides enough context: core operation, single-image scope, return type, and pricing. There is no output schema, but the description adequately states that the result is image content. Explicit guidance on sibling alternatives is missing, but that is already penalized under usage guidelines.
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%, so the input schema already documents all parameters including prompt, image_url, size, background, output_format, and idempotency_key. The description only restates the two core parameters ('원본 이미지' and '편집 지시') without adding new semantic detail, which matches the baseline 3 for high schema coverage.
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 a specific action: editing a single image using an original image and an edit instruction, and returning image content. The phrase '한 장' (one image) differentiates it from batch-oriented siblings like image_batch_create, and the editing framing distinguishes it from image_generate.
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?
The description implies the use case: you have an original image and an edit instruction and want one edited image back. However, it does not explicitly say when to prefer this tool over image_generate or the batch tools, nor does it mention any exclusions or alternative conditions.
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.
Each tool targets a distinct operation: single image generation, single image editing, batch lifecycle, LLM chat, model listing, and text processing. The batch tools are clearly separated from single-image tools by their async/batch scope.
Tool names follow a predictable snake_case pattern with domain prefixes like image_, llm_, and text_. Most names are object+verb, but image_batch_result, image_batch_status, and llm_models use noun suffixes instead, which is a minor deviation.
With 9 tools, the server is well-scoped for an AI API covering image generation/editing, batch image operations, LLM chat, and text utilities. Each tool has a clear purpose and none feel redundant.
Core workflows are covered: single and batch image generation/editing, status/result retrieval, LLM model discovery and chat, plus text polishing and summarization. Minor gaps exist, such as no batch result listing endpoint and no way to retry or cancel individual images, but agents can work around these.