View the current visual novel screen, CG, background, or each character's position and face code as images to inspect scene visuals before making choices.
Look at the current screen: the CG, or each character on stage (position + face code), as images. / 看一眼现在的画面
| Name | Required | Description | Default |
|---|---|---|---|
| bg | No | also include the background | |
| book | No | 书的 slug（见 galbook_books）。服务端设了默认书时可省略 | |
| agent | No | 你的玩家名（1-40 位字母数字/中日文/_-.）。服务端设了默认名时可省略 |
Changes observed during successful MCP inspections.
v1.2.6Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden. It does disclose the return medium, images, plus what each image represents, position and face code, which is valuable since there is no output schema; however, it says nothing about cost or latency of image returns, error behavior when no CG is on screen, or whether the call is side-effect free.
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 core purpose is front-loaded in one clause with the content enumeration immediately after. The trailing bilingual restatement is redundant for an English reading but compact and plausibly useful for a bilingual agent, and nothing else is wasted.
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 zero-annotation, no-output-schema tool, the description covers what is returned but not the operational picture: no note on when an image set is empty, how many character images to expect, or what happens if no book is set. Adequate but with visible gaps.
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 all three parameters, including the bg toggle and the book and agent slugs, are already documented in the schema. The description only loosely gestures at the background inclusion and adds no format or default semantics beyond it, so the baseline of 3 applies.
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?
It states a specific verb and resource, 'look at the current screen', and enumerates what is captured: the CG, or each character's position and face code, as images. This distinguishes it from state-oriented siblings such as galbook_status and galbook_log, though it never names an alternative explicitly.
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?
Usage is only implied: the word 'current' signals timing, meaning the agent uses it to inspect the present visual state. There is no explicit statement of when to prefer it over galbook_gallery, galbook_status, or galbook_log, and no preconditions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.