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

The annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is established. The description adds beyond that by noting pagination ('Paginated (up to 100/page)'), enumerating the six regulatory agencies, and describing the annotation fields. It does not contradict the annotations, and the added context (scope, licensing, pagination) is valuable.

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?

Four sentences, each conveying distinct information (core action, supported agencies, annotation fields, pagination/attribution). The most important action and scope are front-loaded, and the license note is compactly appended. No filler or redundancy.

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 an output schema present, the description does not need to detail the return shape, and it already explains the domain (PGx drug labels), the coverage (agencies and sizes), and the available filter (dosing_only). It is missing mention of default values, but those live in the schema. For a read-only, idempotent API, this is sufficient.

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 schema already documents all three parameters. The description's mention of filtering to dosing-information-only labels paraphrases the dosing_only schema, adding no new syntax or semantics. It does somewhat reinforce the purpose of the dosing_only flag, but nothing is added beyond the schema's own wording.

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 opens with a specific verb and resource: 'Retrieve pharmacogenomics (PGx) drug label annotations from regulatory agencies curated by PharmGKB.' It distinguishes the tool from sibling PharmGKB tools like drug_search and gene_search by centering on regulatory drug label annotations and listing the exact agencies covered. This leaves no ambiguity about what the tool returns.

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 a clear, actionable usage hint: 'Filter to dosing-information-only labels for actionable prescribing guidance,' telling the agent when to set dosing_only=true. It also implies the tool is for regulatory label annotation lookups rather than gene/drug/variant searches, but it never explicitly names alternatives or states when not to use it. The context is clear but exclusions/alternatives are not spelled out.

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