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

With no annotations, the description carries the full burden. It does disclose the output payload (suggested answer structure, structured data type, related content), which is meaningful, but it omits return format details, determinism/confidence behavior, and any read-only/safety context.

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 with the classifying verb early and the output facets trailing. The bracketed tagline is slightly redundant but the whole is compact and wastes little.

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 classifier with no output schema and no annotations, the description adequately conveys what comes back, but leaves the parameter's expected shape and the exact return structure under-specified for an agent to rely on.

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 single parameter q has 0% schema description coverage, so the description must compensate. It implies q is 'a search sentence or question' (一句搜尋或提問), which adds some semantic meaning, but gives no format, length, or language expectations – partial compensation only.

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 (判斷/classify) and resource (a search or question), and enumerates the four intent categories it resolves to. This is clearly distinct from glossary siblings like explain_term or get_howto, though it never explicitly contrasts itself with them.

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 states what the tool classifies but gives no when-to-use condition, no prerequisites, and no routing against alternatives such as search_glossary or explain_term. The agent must infer that this is the entry point when an unclassified query arrives.

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