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

Beyond the annotations (readOnly, non-destructive, closed-world), the description discloses that results come from a real algorithm engine rather than LLM generation, which is genuinely useful trust context for a computation tool. It also enumerates the returned metrics, though it omits that CL/Vd computation depends on the optional dose parameter and says nothing about units or data-quality requirements.

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?

Two compact clauses: a title, the trigger condition, and the returned metrics. Front-loaded with the tool's identity and free of filler, with only mild repetition between the two output lists.

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 no output schema, the description correctly takes on the job of listing return values, which it does explicitly. For a simple read-only computational tool with fully documented parameters this is nearly sufficient; the main omission is the dose-dependency of CL/Vd.

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 each of the four parameters already carries a description and the baseline is 3. The description adds only that time_points/concentrations drive the analysis and that CL/Vd are returned; it does not explain that dose/dose_unit are needed for those two outputs or clarify the string-typed time and concentration arrays.

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 analysis (NCA non-compartmental pharmacokinetics) and the concrete quantities it computes (AUC/Cmax/T1/2), with a bracketed title restating the resource. An agent can tell this is the PK-parameter calculation tool rather than a simulation or PD-evaluation tool, though it never explicitly names the neighboring act_pkpd_eval or act_pkpd_simulate as the alternatives.

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 phrase '用户有血药浓度-时间数据要算 AUC/Cmax/T1/2' implies the triggering condition (user supplies concentration-time data and wants NCA parameters), which is adequate usage guidance. It gives no when-not guidance and does not differentiate from the many PK/PD siblings (act_pkpd_eval, act_pkpd_simulate, act_ic50_fit), leaving the agent to infer routing.

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