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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe and idempotent. The description adds context about the underlying data source (PubMed) and the full index size (~2,000 references), plus the evidence tier classification. It doesn't contradict annotations and adds meaningful context about what the tool does beyond safety.

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?

Two sentences, front-loaded with the core purpose and key detail (evidence tiers), then the filtering guidance. No wasted words; the description includes all essential info without redundancy. It earns its place by covering purpose, tags, filters, and usage in a compact form.

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?

Given the tool's simplicity and rich annotations (read-only, open-world), the description covers everything needed: what it lists, how to filter, how to page, and what the evidence tiers mean. The output schema is absent, so the description doesn't need to describe return format; it suffices for correct invocation. No open questions remain.

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 coverage is 100%, so parameters are well-documented in the schema. However, the description adds value by explaining the experiment_type filter with examples and clarifying that 'Clinical Experiment' maps to human_clinical tier. It also explains the limit parameter's behavior (max 100, fetched upstream) in the schema already, but the description ties parameters to the overall purpose. The description doesn't repeat schema details but adds conceptual context.

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 states a specific verb ('List') and resource ('PubMed-cited papers in HERB's reference index') and explains the purpose (literature backing for herb/ingredient associations). It clearly distinguishes from siblings like herb_search (which searches) and herb_detail (which likely shows a single herb), and mentions the paper detail tool as a follow-up. The evidence tier tagging adds specificity beyond a generic list.

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?

Explicitly states when to use this tool: to list referenced papers, with optional filters by drug type or experiment type, and when to leave blanks (to page through all references). It also hints at when not to use it (if you need detail on a specific paper, you'd use herb_paper_detail, implied by the sibling name). The description provides clear conditional usage and alternatives.

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