whodb_platform_ontology_references

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so safety/idempotence need not be restated. The description adds the useful scoping fact that workspace {host, org, project} targets a single call without mutating session defaults, but that point is largely duplicated by the workspace field description in the schema, and it says nothing about result shape or limits given there is no output schema.

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?

Two tight sentences with the core purpose front-loaded and no filler. The second sentence is partly redundant with the workspace schema description, which keeps it from being fully economical.

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 read-only list tool with 100% schema coverage and no output schema, the description is minimally sufficient. However, with ten parameters including several generic-looking filters (deployed, schema_mode, type) whose relevance to ontology references is unclear, the definition does not help the agent understand which knobs actually apply here.

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 100%, so the baseline is 3 and the schema carries documentation for all ten parameters, including the mechanistic filters (limit/offset, search, fields). The description only highlights the workspace object and never explains which filters are meaningful for ontology references (e.g., whether status/deployed/type apply).

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: list shared ontologies referenced by the selected project, plus their status. That is clearly distinguishable in kind from mutation siblings (add_ontology_record, delete_ontology_record), but it does not distinguish itself from closely related read siblings such as whodb_platform_shared_ontologies, whodb_platform_discover_shared_ontologies, or whodb_platform_ontologies.

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?

There is no explicit when-to-use guidance and no named alternative, despite several near-neighbour tools in the same family (shared_ontologies, discover_shared_ontologies, ontology_reference_impact). The only contextual statement concerns workspace targeting, not tool selection.

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