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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description does add real value beyond that: it states the output is a structured evidence card and that it is produced by a deterministic algorithm engine rather than LLM generation, which is meaningful trust context. It says nothing about how missing or sparse inputs (e.g., only a title, no abstract/DOI) are handled, nor about deduplication or failure modes.

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 short, but the bracketed lead '【文献证据分级录入】' verbatim repeats the annotation title, and 'Decision OS' and '真实算法引擎执行' are packed into run-on fragments without clear sentence boundaries. Information is front-loaded, yet a meaningful share of the text is redundant with structured fields.

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 simple read-only intake tool with four flat parameters and no output schema, the description covers the essential loop: one paper in, a structured evidence card out. It leaves gaps around what the evidence card contains, what input completeness is required, and where this sits in the surrounding decision workflow (followup, report), which matters given the dense sibling set.

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 baseline is 3; the schema itself, however, only labels fields ('DOI', '标题', '摘要', '文献类型') without format or role guidance. The description adds no parameter-level meaning — it never mentions which fields are required or how abstract/literature_type influence the evidence grading. Credit is limited to the schema doing the minimal work.

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 states a concrete verb and resource: taking one piece of literature and structurally decomposing it by evidence grade into a structured evidence card ('按证据等级结构化拆解... 返回：结构化证据卡'). The purpose is clear, but no sibling is named or contrasted (e.g., act_decision_followup, act_decision_report, act_lit_verify_citations, act_checklist_check), so an agent cannot tell which of the decision/literature tools apply. The 'Decision OS' label is unexplained jargon.

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 phrase '用户给一篇文献要按证据等级结构化拆解' hints at the trigger (a user supplies one paper needing evidence-grading), but this mainly restates the purpose rather than providing explicit when-to-use guidance. There are no exclusions, no prerequisites, and no routing to the obvious siblings in this crowded family. An agent must infer the choice among dozens of act_* tools.

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