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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the bar is lower. The description adds meaningful behavioral context: alias resolution across Chinese, pinyin, English, Latin, gene alias, and ID; the fact that multiple name forms resolve to the same record; and that the tool deliberately carries no evidence tiers.

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?

Three sentences with no filler; the first sentence front-loads the core capability and accepted search terms, the second explains the return contract, and the third disambiguates from evidence/relationship tools. Every sentence earns its place.

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 appropriately states that the tool returns matching IDs for herb_detail and preemptively clarifies it has no evidence tiers. Schema covers both parameters fully and annotations cover safety. It does not describe output formatting or empty-result behavior, but that is not critical for a simple lookup tool.

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 baseline is 3; the description adds value beyond the schema by giving concrete alias examples ('板蓝根', 'banlangen', 'Dyers Woad', 'BAN LAN GEN') and explaining that results are matching IDs intended for herb_detail. This enriches the keyword parameter meaning without duplicating 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 action and resource: 'Search HERB 2.0' across herbs, ingredients, gene targets, or diseases. It distinguishes itself from siblings by clarifying that it returns IDs intended for herb_detail and explicitly states it is a name lookup, not a relationship/evidence tool.

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 description provides practical routing guidance by saying the tool returns matching IDs to pass to herb_detail, and excludes relationship/evidence usage. It does not explicitly enumerate when not to use it versus other herb siblings like herb_browse, but the downstream reference gives a clear usage context.

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