Search EUDAMED devices

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely non-obvious traits: upstream name matching may not be partial, exact=true performs local equality matching, and results carry no exhaustive-coverage or conformity guarantee. That caveat set is exactly the kind of context annotations cannot express.

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?

Four dense sentences, front-loaded with the precondition and then the exact/raw/return semantics in priority order. No filler, though the wording is compressed enough that terms like "normalized evidence and source provenance" require a second read.

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?

With no output schema, the description steps in to describe the return shape (normalized evidence, provenance, optional raw device fields) and adds coverage/conformity disclaimers. Combined with annotations, an agent has enough to invoke it correctly; only the per-filter semantics remain thin.

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 20% across 10 parameters, so the description must compensate. It does explain the two behavior-changing toggles (exact does local equality, raw adds original device fields) that the schema leaves undocumented, but the seven identifier filters (basicUdi, primaryDi, reference, tradeName, deviceName, manufacturerSrn, language) remain unexplained and the phrase "restrictive filter" is never tied to specific fields.

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 ("Search public UDI records") plus the hard precondition of at least one restrictive filter. It clearly reads as a device search distinct from the actor/reference/investigate siblings, though it never names those siblings to sharpen the boundary.

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?

"By at least one restrictive filter" gives a real precondition for use, and the exact/raw notes hint at when to escalate to stricter or richer results. But there is no explicit guidance on when to choose this over eudamed_actors or eudamed_investigate, and no statement of which parameters actually count as restrictive filters.

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