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

Annotations already establish read-only, idempotent, non-destructive. The description adds real behavioral value: it discloses the return shape (full cards for supporting and conflicting studies) and the dedupe behavior of repeating studies as short cards. The undefined term 'full_card_in' weakens the disclosure slightly.

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 sentences, front-loaded with the core purpose and usage example. The final sentence is largely redundant with the dedupe parameter description but adds the 'full_card_in' naming that the schema lacks, so it still earns some of its space.

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?

No output schema exists, so the description carries the return-value burden. It gestures at cards for supporting/conflicting studies but omits pagination, result limits, or a clear definition of 'full card' vs 'short card', and the unexplained 'full_card_in' field is left dangling.

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 coverage is only 33%; a and b have no schema descriptions. The description partially compensates by stating 'either direction', clarifying that argument order is irrelevant, but never specifies what a and b actually are (IDs, names, entity types). The dedupe semantics are covered by the schema itself.

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 ('Direct curated relations between two entities (either direction)') and gives a concrete question it answers. It is clearly more targeted than siblings like find_relations or get_relation, but never names those siblings to sharpen the distinction.

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 example question ('what is the evidence that A acts on B?') implies the intended use case. However, there is no explicit when-to-use versus find_relations or get_relation, and no exclusions or prerequisites, leaving routing to inference.

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