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

Annotations declare readOnlyHint=false, so the agent expects some non-trivial operation, but the description says nothing about what is created, whether anything is persisted or returned only in the response, or how long it takes. "RETURNS: 摘要卡" merely restates the tool name and conveys no behavioral context beyond the annotations.

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 text is a pipe-delimited keyword dump: bilingual title repeated, an ALIASES list of five terms, and a RETURNS field that duplicates the name. Only the USE WHEN clause carries actionable information, and it is buried behind noise rather than front-loaded.

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 six parameters, no output schema, and a non-read-only annotation, this tool has real complexity, yet the definition never describes the structure or sections of the returned digest card. An agent cannot tell what it will receive or how to present it, and the alias list does not compensate for that gap.

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%, and each parameter (title, year, journal, abstract, source, external_id) already carries a Chinese description, including the note that an empty abstract lowers digest quality. The description adds no syntax, defaults, or priority guidance beyond that, so the baseline 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?

"The user gives a paper and wants a structured digest card out of it" identifies a recognizable action and input, so the basic purpose is inferable. However, "digest card" is never defined, and nothing distinguishes this from siblings like literature_review_outline, literature_compare, or academic_polish that also consume a paper; the leading title/alias strings repeat the name rather than add meaning.

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 explicit "USE WHEN" clause gives a positive trigger condition, which is more than most definitions offer. But there are no when-not conditions, no prerequisites (e.g. whether a full text or abstract is required), and no named alternative for adjacent tasks such as comparing papers or outlining a review.

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