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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. Beyond that, the description adds only 'RETURNS: 结构化证据卡', which names the artifact without saying what the card contains, how evidence level is assigned, or whether the source text is stored or merely parsed. The alias list and bilingual title are metadata, not behavioral disclosure.

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 pipe-delimited header front-loads the USE WHEN clause, which is good, but the entry is padded by a duplicated bilingual title, an ALIASES list of five alternative names, and a one-word RETURNS line. None of those extras help an agent decide or invoke, so several tokens do not earn their place.

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 read-only, four-parameter intake tool with full schema coverage and no output schema, the definition covers the essentials: what it does, when to use it, and that it returns an evidence card. The remaining gap is that with no output schema the agent cannot predict the card's fields or grading scale, which the description could have sketched in a sentence.

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 doi, title, abstract, and literature_type are already documented in the schema. The description adds nothing about how these inputs affect grading or what happens when only title is supplied, 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 description gives a specific verb and artifact: 'decompose a paper into a structured evidence card by evidence level (Decision OS)'. An agent knows this tool turns a paper into a graded evidence record, not a search or a report. It does not distinguish itself from close siblings such as evidence_report, evidence_followup, or act_lit_digest, so it stops short of a 5.

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 'USE WHEN' clause supplies one trigger condition, but it largely restates the purpose rather than giving real routing guidance. There are no when-not conditions and no named alternatives, even though the sibling list contains several adjacent evidence and literature tools an agent could easily confuse with this one.

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