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

With no annotations, the description carries the full burden, and it does disclose real behavioral scope: it is an informational lookup bounded to three named drugs and explicitly excludes dosing advice. Safety-relevant content (severe warnings, when to seek medical care) is flagged. It still does not say whether the content is static reference material or how current it is.

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 front-loaded sentence: domain tag first, then the covered content, then the hard exclusion. Dense but every clause adds a distinct content category; only the parenthetical drug list makes it slightly heavy.

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 and no parameters, the description is essentially the whole contract, and it does define what the returned page covers plus its boundary. Missing minor items: whether the three drugs are exhaustive and any freshness/source-date caveat.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. It correctly implies a no-input retrieval rather than misleading the agent into expecting filters.

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?

States a specific resource (Taiwan-approved GLP-1 weight-loss drugs) and enumerates exactly what it returns: incidence rates, serious warnings, when to seek care, TFDA reminders. It even names the individual drugs (tirzepatide, semaglutide, liraglutide), which disambiguates it from the other health__* tools at a glance.

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 subject matter makes the trigger obvious (a question about GLP-1 side effects), and the closing clause '不提供劑量建議' explicitly carves out a when-not case. However, it names no alternative sibling to route dosage or general-medication questions to, so it stops short of full routing guidance.

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