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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the description's main added value is 'RETURNS: 研究计划文本', which tells the agent the output is plan text. It never says whether anything is persisted or what happens when 'design' is omitted, leaving the non-read-only hint unexplained.

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 front-loading puts the trigger condition and return type where an agent will see them first. The alias list is long but serves a real matching purpose, and no sentence is filler.

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 two-parameter generator with no output schema, the definition covers what it does, when to call it, and the shape of the result. The only real gap is the unexplained non-read-only behavior and the role of the optional 'design' field.

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% with only two parameters, both already documented as 研究主题 and 研究设计类型, so the schema carries the parameter burden. The description adds no syntax, format, or effect information for 'design', which is the one field whose impact an agent would want explained.

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 concrete verb-plus-resource reading: it produces a staged plan with milestones and an order of work for a chosen topic, which is more specific than the bare name. It stops short of distinguishing itself from the sibling experiment_plan_generate, so an agent must infer that this one is topic-level rather than experiment-level.

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 states the triggering condition clearly (user wants a staged plan / milestones / ordering for a chosen topic). There are no exclusions or named alternatives, so it is clear context without routing guidance away from look-alike tools.

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