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

Annotations already declare readOnly/idempotent/openWorld, so the description correctly focuses on non-obvious behavior: AND semantics, the no-fallback rule for identifier filters, pagination via nextOffset, and the interpretive caveat that an evaluation is not a prescribing recommendation. That caveat is genuinely valuable context an annotation cannot express.

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?

Six short clauses, front-loaded with the resource and filter modes, then the AND/fallback rules, then return contents and pagination. No sentence is redundant with the schema or with another sentence.

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 12-parameter, all-optional search with full schema coverage, annotations, and an output schema, the description covers everything left unsaid: parameter interaction, return contents useful for chaining, pagination, and the interpretation warning. Nothing an agent needs in order to call it correctly is missing.

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 the baseline would be 3, but the description adds cross-parameter rules the schema cannot encode: filters are ANDed and identifier filters do not fall back to name-only matching. Those interaction semantics materially change how an agent composes a query, so it earns above baseline.

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?

States a specific verb (Search) and resource (evaluated gene–drug pairs) and enumerates the filter dimensions an agent can use, which makes it clearly distinct from pgx_search_alleles and the other siblings. It stops short of explicitly naming the sibling it is not, so it lands just below the top band.

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?

Gives clear operating context: filters combine with AND, identifier searches never degrade to name matching, and results carry guideline links for pgx_get_guideline, which routes the agent to the correct next tool. It offers no explicit when-not or alternative-tool exclusion, so a 4 rather than a 5.

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