Pixiv 原图下载

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

Since no annotations are supplied, the description must carry the full behavioral load, and it does disclose the key traits: a local-filesystem write into PIXIV_MEDIA_DIR, refusal rules for disallowed works, a 10-page ceiling, and concurrency governed by PIXIV_DOWNLOAD_CONCURRENCY. It omits overwrite behavior for pre-existing files and any auth/cookie requirement, which matter for a writing tool.

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?

Four dense sentences lead with the core action and destination, then constraints, then limits, with no filler. Every clause carries operational information.

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?

There is no output schema, but the description states what is returned (per-page absolute paths plus work metadata), which compensates. The remaining gap is file-collision/overwrite and error behavior on refusal for a tool that writes to disk with no annotations to fall back on.

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 schema already documents pid, r18, pages, and allow_gray in detail; the description adds only the page cap, which schema maxItems already conveys. Baseline 3 applies because the description adds little parameter meaning beyond the structured fields.

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?

States a specific verb and resource (download original images by PID) plus the destination directory and the return payload (absolute per-page paths and work metadata). This clearly separates it from the read-only siblings pixiv_search and pixiv_illust_detail, which cannot write files.

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 spells out the conditions under which the tool refuses to act (blacklist, unapproved gray list, AI, animated) and caps the operation at 10 pages, so the agent knows the boundaries before calling. It does not explicitly route the agent to pixiv_search or pixiv_illust_detail to obtain the PID, which is the only missing piece.

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