Disease Target Evidence

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds real value beyond them: it defines the 0–1 evidence-score scale per data type and explains that drug_count and tractable are per-row observed values that are null only when the source omits them.

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 purpose and example are front-loaded, which is good, but the seven-bullet evidence-type glossary is reference material that likely duplicates the output schema and dilutes the operative guidance. Roughly half the text is data dictionary rather than call guidance.

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 need not explain return values, and annotations cover safety. What an agent needs to call correctly — ID formats accepted, score semantics, default filtering behavior, and an end-to-end example — is all present.

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?

The schema itself documents all four parameters, so the schema-coverage signal understates the situation. The description still adds meaning: it clarifies what the score threshold (min_score) is measuring via the per-data-type breakdown, defines 'tractable' as any Open Targets tractability bucket, and gives a worked example with a concrete MONDO ID and limit.

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 and resource — 'Return top protein targets for a disease' with Open Targets evidence scores — which is far more precise than the bare name. It doesn't, however, explicitly distinguish itself from the directionally-opposite or overlapping siblings get_target_diseases, get_common_disease_targets, and compare_disease_target_overlap.

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?

Usage is only implied: the example call shows invocation syntax, but nothing says when to prefer this over get_target_diseases (gene→disease direction) or get_common_disease_targets (multi-disease). No prerequisites or exclusions are stated.

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