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

Annotations already state readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description does add that it returns matched samples plus a balance assessment and that a real algorithm engine (not an LLM) executes it, which is useful context; however it omits prerequisites such as minimum sample size or data format expectations.

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 definition is a single compact block: bracketed label, usage trigger, return value, and execution note. Every fragment carries information and the tool name is front-loaded, with no 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?

With four parameters, no output schema, and a simple read-only operation, the description covers what the tool does, when it applies, and what it returns (matched sample and balance). Only the input data expectations and matching-algorithm specifics are left implicit, a minor 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%, so all four parameters (data, ratio, treatment, covariates) are already documented. The description's mention of '1:1 匹配' loosely maps to the ratio parameter but adds no syntax or constraint detail beyond the schema, 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 specific technique (倾向性评分匹配 / PSM) with the action of matching, so an agent knows this performs propensity-score matching rather than a generic statistic. It does not explicitly distinguish itself from related siblings such as act_iptw or act_smd_balance, 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?

Phrases like '用户要做 PSM、倾向评分匹配、1:1 匹配基线' imply the usage context (baseline balancing via 1:1 matching), but no explicit when-not conditions or alternative tools are named. An agent must infer that IPTW or SMD balance tools are the alternatives.

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