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.

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

With no annotations, the description carries the full burden. It usefully discloses a non-obvious behavior — the tool computes a 'compliant' verdict using black/graylist rules — but '同一套规则' is undefined, and it never says what a non-compliant result looks like (error vs. a compliant:false field), whether Pixiv auth/refresh tokens are required, or whether rate limits apply.

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?

Two tight sentences: the read-and-return-fields contract is front-loaded and the non-download constraint closes it. No filler, and the returned-field list is compressed rather than enumerated in prose.

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?

With no output schema, the enumerated return fields are exactly the right compensation, and the compliance-verdict behavior is a valuable addition. What's missing is the failure mode for non-compliant works and any auth prerequisite — notable gaps for a tool whose output is a policy decision, but not fatal.

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%, including detailed enum semantics for allow_gray and the conditional meaning of r18, so the schema already does the heavy lifting. The description only restates that lookup is keyed on PID; it adds no format or validation detail beyond the schema.

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 ('按 PID 读取作品元数据') and enumerates exactly what comes back: title, artist, tags, bookmarks, page count, original image URLs, rating. It also explicitly disclaims the download behavior, which cleanly separates it from the pixiv_download sibling.

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 only routing signal is the trailing '不下载', which implicitly points download intent at pixiv_download; it never mentions pixiv_search as the way to obtain a PID in the first place. Some when-to-pass guidance lives in the schema (allow_gray: '只有用户明确点名时才传'), but the description body itself leaves usage to inference.

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

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses blacklist rejection of the entire request, automatic filters (mutual-exclusive character tags, aiType=2, animations), gray-list default avoidance, R-18 limited to official xRestrict, 1.5-year half-life favorite sorting, session-level deduplication, and a 15-second cooldown. It also states that files are written to local disk and metadata is returned, which is exactly the beyond-schema behavior an agent needs.

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?

A single dense paragraph, but the core purpose is front-loaded in the first sentence and subsequent clauses are rules rather than filler. The closing caption/display instruction is presentation guidance rather than invocation semantics, which slightly dilutes focus, but nearly every sentence earns its place given the tool's complexity.

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 5-parameter tool with no output schema and no annotations, the description covers filtering behavior, ordering, session semantics, rate limits, credential requirements for r18, and what is returned (local paths plus metadata, with caption format). An agent has everything needed to call it correctly and set user expectations.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: multiple tags are AND-ed against tags or titles, session isolates dedup history and cooldown, and allow_gray categories must genuinely be present or the item is rejected. It also warns that unmapped Chinese names should be converted to Pixiv-style Japanese tags, which the schema does not convey.

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 opening sentence states a specific verb + resource + full outcome chain: search Pixiv illustrations by character/tag, download originals locally, return file paths and metadata. The scope (character/tag-driven search plus download) is distinct enough that an agent can tell it is the discovery+fetch tool rather than a detail or raw-download tool.

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?

It gives concrete when-to-use rules for the risky options: allow_gray only when the user explicitly names a category, r18 only on explicit request, gray-list items must genuinely be present, and it advises pre-translating tags not in the built-in mapping. It stops short of explicitly contrasting with pixiv_download or pixiv_illust_detail, so sibling routing is left implicit.

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