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

Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description adds rich behavioral context beyond that: computational_prediction is defined as hypothesis-level, traditional_use is distinguished from clinical trial evidence, and pagination semantics (total vs truncated) are disclosed. It also warns against misrepresenting predicted edges as proof.

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?

The description is long but every sentence carries specific, non-redundant value. It front-loads the core purpose and then covers evidence tiers and pagination; the only minor cost is length, but the density is justified for a complex data tool.

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?

There is no output schema, so the description carries the full burden of explaining return structure, and it does so: relationship rows include evidence_tier, paged tables have {total, offset, limit, returned, truncated, rows}, and `truncated:true` signals more rows. The evidence-tier semantics and section-narrowing guidance make the tool fully usable without external documentation.

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?

Although schema coverage is 100%, the description adds meaning by explaining the default 25-row return, the significance of `total` as the true upstream row count, and how `sections` can narrow the payload. This exceeds the schema's parameter descriptions and helps an agent choose values intelligently.

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 resource ('Full record for one HERB id') and enumerates the four category variants (herb, ingredient, target, disease) with their component contents enough to distinguish the tool from herb_search or herb_browse. It also states the evidence-tier labels clearly, making the operation's scope unambiguous.

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 gives concrete operational guidance: use `sections` to narrow, use `offset` to page, and expect `truncated:true` when more rows exist. It does not explicitly compare against sibling tools like herb_browse or herb_search, but it clearly explains when this detail endpoint is appropriate and how to avoid pulling huge result sets.

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