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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered by structured data. The description does add genuine value by stating the result comes from a real algorithm engine rather than an LLM ('真实算法引擎执行，非大模型生成'), which tells the agent to trust the output as deterministic. It does not explain what happens when some or all of the optional inputs are omitted, which is a real gap for a tool with zero required parameters.

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 short, labeled segments ('【毒理评估】' and '返回：') with the purpose front-loaded and zero filler. It is appropriately sized for a four-parameter scoring tool, though the bracketed label format is slightly cryptic compared with plain prose.

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 the input concept (candidate compound toxicity) and the output shape (risk grading), which is reasonable given there is no output schema. But for a tool where every parameter is optional, it never says whether all four inputs are needed for a valid grading or how partial inputs are handled, leaving a meaningful behavioral 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 the four parameters (logP, hERG IC50, daily dose, expected Cmax) are already documented by the schema. The description mentions the hERG endpoint but adds no meaning about units, acceptable ranges, or which inputs drive which endpoint. Baseline 3 is appropriate when the schema carries the detail.

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 uses a specific verb+resource ('评估候选物的毒性风险') and enumerates the endpoints covered (hERG/DILI/遗传毒), so an agent can tell what it computes. However, it never distinguishes itself from the sibling tool act_tox_predict, which by name appears to occupy overlapping territory, leaving the agent to guess which one to call.

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?

Usage is only implied via the phrase '用户要评估候选物的毒性风险', which describes the trigger condition but gives no exclusions, prerequisites, or comparison to alternatives such as act_tox_predict or act_pkpd_eval. The agent knows roughly when the tool is relevant but has no routing guidance.

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