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

With no annotations, the description carries the full behavioral burden and does so: it discloses the exact failure mode, the machine-readable error code, and the informational content of the refusal. Nothing about its runtime behavior is left to inference.

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?

A single sentence, front-loaded with the 'Not served' verdict so the agent learns the critical fact first. The trailing clause is slightly dense but every element (refusal code, what it names) carries information.

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 zero-parameter refusal stub with no output schema, the description is essentially complete: it explains the outcome of any call and what the refusal message contains. The only omission is pointing to the sibling that actually serves this data.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no meaningful inputs are consumed, matching the open object schema with additionalProperties.

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 explicitly frames the tool as an unimplemented stub ('Not served') and names the exact resource (EuroVoc descriptors, directory codes, subject matters of EU works), so an agent knows precisely what it would have covered. It is distinguishable from siblings like classification or search, though it never states the positive purpose these siblings serve.

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?

It tells the agent unambiguously what happens on every call (typed refusal retrieval_mode_unavailable) and that the refusal names which modes are served and what data would serve them — effectively 'do not call this'. It stops short of naming a concrete sibling to use instead for this data.

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