traverse_biological_graph

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

With no annotations, the description carries the full burden and does so well: it discloses that hops report source database and score, that scores are products of weights and NOT probabilities, and that literature edges are keyword hits. It stops short of permissions, limits, or performance characteristics, but the semantic caveats are 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?

Front-loaded purpose followed by clearly separated Args and Returns sections; each line carries information. The '(PRD-22)' tag is extraneous, but overall the structure is efficient and scannable.

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 five-parameter traversal tool with no annotations, the description covers inputs, scoring semantics, edge provenance, and the return shape. It is nearly sufficient, missing only guidance on result size/pagination and how to choose among competing graph tools.

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 0% for all five parameters, yet the description documents each with an example or format ('TP53', 'MONDO:0005575', 'colorectal cancer'), numeric ranges (1 to 6, 0.0 to 1.0), defaults, and the full target_type vocabulary — fully compensating for the empty schema.

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 definition states a specific verb and resource ('Enumerate graph paths from a source gene to a target entity') with the scope of traversal clearly bounded by source and target. It is largely distinguishable from siblings such as build_entity_subgraph, though it never explicitly contrasts itself with that close alternative.

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 implied by the source-to-target framing, and one conditional rule is given ('Literature edges ... are only used when target_type is publication'). However, there is no explicit guidance on when to prefer this over build_entity_subgraph or other graph/pathway siblings, leaving tool selection to inference.

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