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

With no annotations to lean on, the description carries the full burden and does so: it discloses the exact failure behavior (typed refusal retrieval_mode_unavailable), the cause (data not acquired), and the payload content of the refusal. There is no ambiguity about what a call produces or why.

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 verdict 'Not served' is front-loaded so the critical information lands first. The single sentence is long and clause-heavy, packing cause, behavior, and routing into one breath, but no clause is redundant.

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 stub with no annotations and no output schema, the description answers every question an agent could have: is there data, what happens on call, what does the response say, and where to go instead. Nothing actionable is missing.

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 declared parameters and the schema is a permissive object, so there is nothing for the description to document; the baseline of 4 applies. It does not mention that arbitrary arguments are accepted and ignored, which is the only gap.

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 opens with an unambiguous verdict ('Not served') and names the exact resource (transposition links between EU directives and Luxembourg measures), so an agent knows immediately this endpoint provides no data. It also contrasts itself against the retrieval modes that do work, making it distinguishable from every sibling without opening 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?

It states that every call returns the same typed refusal, which is an explicit 'never call this expecting data' signal, and it routes the agent to the modes that are served (citation, cited_by, relations) — all of which are actual sibling tool names. When-to-use (never, except to observe the refusal) and the alternatives are both present.

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