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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds real context on top: the exact returned fields (slug, substance, strength, form, rx/otc, refunded, sold_online), the data provenance (RPL and the Ministry of Health refund announcement), and the meaning of those flags (prescription items are shown for information only and are not sold online, refund prices are official maximums). The only weakness is that some of the behavioural text covers storefront shipping policy, which is tangential to a search operation and duplicated in search_shop_policies_and_faqs.

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 opening sentence is well front-loaded and states the verb, scope and returned fields. However, roughly a third of the text covers delivery logistics (courier only, no parcel lockers, PLN gross) that does not affect how this tool is invoked and belongs to the shop-policy sibling, diluting an otherwise tight definition.

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 two-parameter read-only search with no output schema, the description is nearly sufficient: it enumerates the response fields, explains the rx/otc and sold_online semantics, states the data sources, and enables chaining via slug. It stops short of describing matching or empty-result behaviour, so a 4 rather than a 5.

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 100%, with both query (brand or substance, with examples) and limit (1-20, default 10) documented in the schema. The description only restates the brand-or-substance matching mode and adds nothing on match behaviour such as prefix versus fuzzy matching or what happens on zero results, so the schema-baseline of 3 applies.

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 the Polish register of authorised medicines, matched by brand name or active substance. It also names the sibling tools it feeds into (get_medicine, get_medicine_document, get_refund_prices) via the returned slug, so an agent can distinguish it from search_catalog and get_medicine without opening schemas.

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 clear next-step guidance: use the returned slug with get_medicine, get_medicine_document or get_refund_prices, which establishes the search-then-detail workflow. It does not explicitly state when to prefer it over sibling search_catalog or compare_medicines, so the alternative-selection guidance is incomplete.

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