Find Drug-Gene-Disease Network

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered; the description adds genuinely new behavioral context by explaining the per-seed resolution rules and warning that graph contents depend on ingestion or retained historical versions. It does not mention pagination, size limits, or what an empty/partial neighbourhood looks like, but the core caveat about data provenance is the most valuable part.

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?

One-line purpose statement up front, followed by a single dense sentence enumerating the three resolution branches. Nearly every clause carries information; the only slight waste is the semi-related note about where the store came from, which is valuable but could be trimmed.

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?

An output schema exists, so return-value detail is unnecessary, and the description covers seed handling, traversal scope, and data provenance. One residual tension: it says it expands the 'immediate neighbourhood' while max_hops defaults to 2 with a maximum of 3, leaving unclear whether a 2-hop default exceeds 'immediate'.

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?

Although the coverage metric reports 0%, the schema itself carries a rich 'seed' description with three concrete examples and a min/max/default-annotated 'max_hops'. The description still adds real meaning beyond that by stating what each seed kind resolves to (gene symbol to proteins and variants, UniProt to its stored protein record, MONDO to indicated drugs), which is not derivable from the schema examples.

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 leads with a specific verb+resource ('Traverse the local knowledge graph from a seed entity') and then defines exactly what the traversal returns for each of three entity types, which is far more precise than the title's 'Drug-Gene-Disease Network'. It does not explicitly name the sibling it replaces (e.g. map_disease_drug_landscape or get_disease_targets), so differentiation remains inferential.

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 seed-type breakdown implicitly tells an agent when this tool applies, and 'the store is populated by the storage API, or retained from historical database versions' signals that results are bounded by what was ingested. However, there is no explicit when-not guidance and no alternative tool is named for broader or live queries.

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