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

Annotations already declare the safe read-only, idempotent, closed-world profile; the description goes well beyond that by disclosing the filtering rule (CPIC level-A, allele-positive), the meaning of derived output fields (discordant = present in exactly one; whose_hla = both/recipient_only/donor_only), the source corpus (CPIC/PharmGKB), the keying (two-field HLA allele), and the 'reports both, decides nothing' decision-support caveat. That is rich context an agent cannot get from the structured fields.

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 generative sentence is front-loaded and each subsequent sentence adds a distinct fact (screening parity with pgx_lookup, output field semantics, guideline source, decision-support caveat). It is dense and jargon-heavy with a long parenthetical citation, which costs a point, but little is genuinely redundant.

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 nested-schema tool with an output schema present, the description supplies everything the agent still needs: what gets screened, which associations qualify, how each output marker is defined, and the interpretive caveat that both genomes are reported without a recommendation. No material gap remains.

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% and both nested objects are self-described, so the schema carries the parameter burden. The description adds only that lookups are keyed by 'two-field HLA allele' and restates the 'allele strings only, no patient identifiers' constraint already in the schema, so the baseline 3 is appropriate.

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 first sentence names the specific operation (which genome carries each actionable HLA-drug association for a donor-recipient pair) with an explicit verb and resource. It further differentiates itself from the sibling pgx_lookup by stating it 'screens both typings as pgx_lookup does', so an agent can tell the two apart without opening either schema.

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?

It establishes the triggering context clearly: a donor-recipient pair after an allogeneic transplant, where the recipient's blood carries the donor's genome. It references pgx_lookup as the single-typing analogue, implying the alternative, but never states an explicit when-not-to-use or a hard prerequisite, so it stops short of a 5.

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