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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description adds nothing on behavior beyond 'RETURNS: 实验方案', which merely restates the purpose. It does not say whether the generated plan is persisted anywhere (relevant given readOnlyHint=false), how long/complex the output is, or what the optional inputs do to the result.

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 template front-loads the USE WHEN condition and keeps the body to a few lines. The cost is redundancy: the bilingual title is repeated and the long alias list is mostly search-keyword padding rather than guidance.

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 10-parameter generator with no output schema, the description should hint at what the returned plan contains and how flags like uses_animals, involves_gene_editing or budget_level shape it. 'RETURNS: 实验方案' is all the agent gets, so the definition is adequate but thin relative to the tool's complexity.

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% and every one of the 10 parameters carries a Chinese description including defaults and the note that the deprecated 'prompt' key was replaced by 'research_question'. The description itself contributes no parameter meaning, 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 names a concrete deliverable — an animal or cell (bench) experiment plan for basic research — and a Chinese title plus aliases pin it down. It is clear what the tool produces, though it never states the generating verb or contrasts itself with adjacent plan-type siblings such as topic_research_plan.

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: the user needs an animal or cell experiment plan (basic research)' clause gives a clear trigger condition. It stops short of exclusions or named alternatives, so an agent must infer that clinical/human study design or topic ideation belongs to someone else.

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