build_entity_subgraph

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

No annotations are provided, so the description carries the full burden. It does disclose the output shape (nodes, edges, weights, provenance), which tells the agent this is a computational read rather than a mutation. However, it never states whether anything is persisted, what the relative cost/latency of the multi-source fan-out is, or how failures in one source are handled.

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 a scannable layer list and standard Args/Returns blocks. The Args section largely restates the parameter names and repeats defaults already present in the schema, which is mild redundancy, but nothing is buried or padded.

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 six-parameter multi-source aggregation tool with an output schema present, the description covers the data provenance and each parameter's effect, so the agent knows what it will get and how to shape it. The notable gap is the absence of any runtime/cost expectation, which matters for a tool that orchestrates six external queries.

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% and the schema carries only bare titles, so the description does the documenting work: it explains query as a gene symbol or alias with concrete examples, taxon_id as an NCBI Taxonomy ID defaulting to 9606, and states which data source each include_* flag toggles. It does not clarify how flags interact or whether disabling all of them still returns something useful.

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 (Construct) and resource (ontological Knowledge Subgraph centered on a biological entity) and enumerates exactly which layers get connected (UniProt proteins, Ensembl transcripts, Reactome pathways, GO terms, Open Targets diseases, Europe PMC literature). This distinguishes it from siblings like traverse_biological_graph or get_pathways, which retrieve slices rather than assemble a multi-layer subgraph.

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 layer list, but there is no explicit statement of when to use this aggregate builder versus the many narrower siblings (traverse_biological_graph, get_pathways, get_target_diseases, get_supporting_publications). No preconditions, no cost/latency warning despite this clearly fanning out to six external sources, and no exclusions.

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