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

Goes well beyond the annotations: discloses price ($0.01, RULED), the x402/USDC payment handshake and the exact retry path at _meta["x402/payment"], the free-refusal semantics for barred and ambiguous shapes, and the conservation of acknowledgement text in every payload. These are operational facts an agent cannot infer from readOnlyHint/destructiveHint alone.

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?

Everything sits in a single dense run-on sentence with internal references like 'DESIGN.md §2', which is noise for an external agent, and the actual action is buried behind a long parenthetical field list. The content is mostly useful but not front-loaded.

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 correctly takes on the return contract by enumerating fields, the source UTC stamp, and the fixed acknowledgement lines. Payment and error paths are covered. It does not state the response envelope or whether the result is a single object, a minor residual gap.

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 0%, so the description must carry the load, and it does: it states that exactly one identity may be supplied, that name and INN are matched exactly and case-insensitively, and that ambiguity produces a refusal listing candidates. Only the ema_product_number format (e.g. EMEA/H/C/…) is left unexplained.

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 identifies the resource: one EMA centrally authorised medicine at the latest held generation, with an explicit enumeration of the served fields. An agent knows exactly what comes back. It stops short of a crisp verb-first statement and never contrasts itself with the sibling ema_changes, so the differentiation is only partial.

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 gives concrete routing advice: a free pre-check exists at ema_record_preflight, and ambiguous identities are refused with candidate product numbers listed, which tells the agent how to recover. It also states the hard exclusion (no dosage, claims, availability judgement, or SmPC/leaflet text), steering those queries elsewhere. What's missing is guidance on when to use this versus ema_changes.

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