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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuine non-annotation context: every returned relation cites governed claim IDs and/or evidence registry IDs, which tells the agent about provenance guarantees and how to trace results back to governance records.

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?

Three dense sentences are front-loaded with the purpose and data model, then the filter options. The trailing 'Also GET /api/tools/relations' is a REST endpoint aside that adds little for an agent already invoking the tool, a minor bit of waste.

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 no output schema and five optional parameters, the description carries most of the burden and does cover the graph model, provenance citations, and filterable dimensions. It is still silent on result shape, ordering, and how the limit interacts with pagination, leaving small gaps for a query tool of this breadth.

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 only 40%, so the description must compensate. It does so well for 'predicate' by enumerating all fifteen allowed values (treated_by, evaluated_by, contraindicated_by, etc.), which the schema leaves as a bare string with no enum. However, 'limit' (max 25) and 'claim_id' receive no explanation in the description, and 'node' is only loosely restated as subject/object text.

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 – 'Query the evidence-backed clinical relationship graph' – and immediately defines the data model as subject–predicate–object triples over diseases, medications, tests, findings, and guidelines. This clearly distinguishes it from siblings like get_claims or search_gi_verifications without needing to open a schema.

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 description lists the filter axes (node text, predicate, kind, claim_id), which implies how to use the tool, but never states when to choose this over get_claims or get_evidence_bundle, which also deal with claims and evidence. Usage is inferable from the filter set rather than explicitly guided.

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