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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so safety is covered. The description adds one genuinely useful behavioral fact — that a real algorithm engine computes results rather than an LLM — plus the shape of the return (risk grading). It says nothing about invalid SMILES handling, runtime, or determinism across endpoints.

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?

A single compact line with the tool label, trigger, and return value front-loaded; every clause carries information. The bracketed label partly duplicates the annotation title, which is the only waste.

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 read-only predictor with no output schema, the description covers purpose and return type adequately. Gaps remain around the endpoint enumeration (the schema lists Ames, the description does not) and error behavior for malformed molecules, which matter for correct invocation.

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 both parameters (smiles, endpoints) are already documented in the schema, and the baseline of 3 applies. The description mentions hERG/DILI but not the third supported endpoint (Ames) nor any format expectations for the SMILES string, so it adds no meaning beyond the schema.

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 verb+resource (toxicity prediction) and scope (hERG/DILI, cardiac/liver risk) with a stated return value. It does not differentiate itself from the sibling act_tox_eval or the broader toxicity-evaluation tools, so the agent must infer the boundary.

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 '用户要评估化合物心脏/肝毒性风险' gives an implied trigger condition, but there is no explicit when-not guidance and no named alternative. The agent is not told when to prefer this over act_tox_eval or act_ddi_check.

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