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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the burden is lighter. The description usefully adds that results come from a real computation engine rather than LLM generation, which matters for trust. It does not disclose the balance threshold used for the judgment (e.g., SMD < 0.1) or the output shape beyond a one-line summary.

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?

Three compact, front-loaded statements (what it is, when it is used, what it returns), with no wasted prose. The bracketed label largely repeats the tool title, which is minor redundancy rather than bloat.

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?

The description covers purpose, trigger, and return content, which is the essential core for a two-parameter tool with no output schema. However, it leaves open how the covariate data and grouping vectors are actually supplied (no dataset/session reference exists in the schema), and it omits the balance criterion behind the judgment, so an agent could still mis-invoke it.

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 baseline 3 applies; the description adds nothing about the two parameters. This is a gap because the schema itself is confusing — 'treatment' is typed as an array of strings labeled '分组 0/1' and 'covariates' is typed as an array of strings but described as a sample-by-variable matrix — and the description does not resolve that ambiguity or explain where the underlying data comes from.

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 specific verb+resource: computing standardized mean differences per covariate and a balance judgment, in the post-PSM/IPTW context. That distinguishes it from upstream siblings like act_psm_match and act_iptw, though it never names them explicitly.

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?

It gives a clear triggering scenario ('after the user does PSM/IPTW, check covariate balance'), which is enough to select it over generic statistics tools. It offers no exclusions or explicit alternative routing (e.g., act_table_one for descriptive comparison), so it falls short of a 5.

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