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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds meaningful context beyond that: the dataset size (164k rows), genuine offset+limit pagination with total row count in the response, and the row granularity (product x authorisation-country). The caveat that this is 'not a top-N sample' is a useful behavioral trait for planning queries.

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?

Front-loaded with the resource and scope, then example questions, then query semantics, then pagination — a logical progression. Slightly dense in one long sentence but no filler; each clause earns its place.

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?

No output schema exists, so the description responsibly fills in return-shape facts: one row per product x country, total count available for pagination. Combined with 100% schema coverage and full annotations, this is nearly complete; only the exact row fields are unstated, which is a minor omission for a search tool.

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 already 100%, so the baseline is 3. The description reinforces key semantics — free-text matches product name, active substance, and holder name, and pagination returns a total row count — which helps the agent interpret offset/limit behavior. It adds modest value over the schema, so a 4 is fair rather than a floor.

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 (Search) and resource (EMA Article 57 database) with scope explicitly enumerated: centrally, mutually-recognised, decentralised and nationally authorised products, one row per product x country. This granularity lets an agent distinguish it from ema_article57_product, which presumably returns a single product.

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?

Provides concrete example questions the tool answers (which countries is X authorised in, who is the MAH, what does company Y hold), which clearly orients usage. It also cross-references ema_article57_dataset_info for the country list. It stops short of explicitly stating when to prefer this over ema_article57_product or ema_article57_recent_changes, so a 4 rather than 5.

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