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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safe/read-only nature is covered. The description adds the key behavioral nuance that exporting is not filing and introduces the conditional refusal for non-negligible verdicts when exporting to TRACES. This is valuable context beyond the annotations and does not contradict them.

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 two sentences with zero filler. The first sentence front-loads the action and output formats; the second adds the filing clarification and the refusal condition. Every clause carries necessary information, and the structure is ideal for quick agent scanning.

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 tool with three parameters, an output schema, and strong annotations, the description provides all necessary operational context: what the tool does, what it doesn't do (filing), and a critical edge case (refusal). The output schema covers return shapes, and parameter details are fully described in the schema. Nothing essential is missing for correct invocation.

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 every parameter is already explained in the input schema. The description repeats the format names and mentions 'signed' for JSON and 'FeatureCollection' for GeoJSON, but these details are also present in the schema descriptions. The description does not significantly add semantic value beyond what the schema already provides, justifying the baseline of 3.

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 states a specific action (export) on a specific resource (a compiled statement) and enumerates the three concrete output formats (TRACES NT submission XML, signed Annex II JSON, plot boundaries as GeoJSON). It also clarifies that this is not filing, distinguishing it from submission-oriented tools. This is precise and sets it apart from siblings like eudr_list_statements or eudr_prepare_dds.

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 clearly states that exporting is not filing and nothing is submitted to any authority, which tells the agent when not to use this tool for filing purposes. It also warns that TRACES export is refused for a non-negligible verdict, implying an alternative format might be needed. However, it does not explicitly name alternative tools or provide explicit 'use this instead' guidance for the refused case, so it stops short of a 5.

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