eurlex_citations

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

Beyond the annotations (readOnlyHint, idempotentHint), the description reveals additional behavioral nuances: the balanced split ensures recent cited_by entries do not crowd out cites, the response includes a counts field, and the limit is not back-filled. These details are not present in the annotations and help set expectations for the response shape and edge cases.

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?

The description is concise and front-loaded with the main purpose, then elaborates on the direction behavior. However, there is some redundancy: the balanced split and counts field are described, then repeated with alternative wording about the limit division. This repetition adds a bit of bloat but does not obscure meaning.

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?

The description covers the tool's core behavior, including defaults, edge cases (fewer results when balanced), and a key response field (counts). The context signals indicate an output schema is available, which would supply the full response structure. Overall, the description is sufficient to call the tool correctly without missing critical information.

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 100% and each parameter has a descriptive entry, including enum values and defaults. The description adds a little extra context for the 'direction' parameter (e.g., explaining the balanced split in more narrative form), but it largely echoes the parameter descriptions. Since the schema already carries the semantic weight, the additional description provides only marginal value.

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 description clearly states the verb ('Finds') and the resource ('citation relationships for an EU legal act'), distinguishing it from sibling tools like eurlex_search or eurlex_metadata. It also specifies the key directional options and the balanced split behavior, making the tool's purpose unambiguous.

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 provides strong contextual cues about when to use the tool (e.g., when citation relationships are needed) and explains the behavior of the 'direction' parameter, including the balanced split and potential reduction in results. It does not explicitly name alternative tools or exclusion criteria, but the detail is sufficient for a typical caller to decide when to invoke it.

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