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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds real context beyond them: the eligibility filter (adult/restricted/voucher/top-up exclusion), the fact that it reads the Bestshopping catalog only and never browses merchant sites or activates tracking, and the 18+ cashback constraint. Only pagination/result-shape behavior is left implicit.

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?

Three front-loaded sentences: capability, exclusion scope, then data-source/eligibility boundaries. Each earns its place, though the closing 18+ cashback sentence is user-eligibility policy rather than tool behavior and is the weakest of the three.

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 rich annotations and a declared output schema, return values need no narration, and the description covers what makes this tool distinctive (eligibility filtering, read-only catalog access, no tracking activation). The one real gap is pagination guidance for limit/offset, which neither the description nor the schema text supplies.

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 50%: query and market are documented, limit and offset are not. The description's 'by name, domain or ID' essentially restates the query schema text and 'selected Bestshopping account market' restates market, adding no syntax or format detail, and it says nothing about limit caps or paging via offset. Borderline baseline 3 is appropriate given the schema does half the work.

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 eligible retail merchants ... by name, domain or ID') plus the catalog it reads, which clearly separates it from the single-record get_merchant sibling. It stops short of naming any sibling or stating the singular-vs-list distinction outright, so it is clear but not maximally differentiating.

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?

The exclusion list ('exclude adult shops, restricted categories, digital vouchers, top-ups and services') implicitly bounds when this tool is useful, and 'does not ... activate tracking' hints at the boundary with prepare_cashback_link. But no explicit routing advice is given — nothing says to use get_merchant for a known ID or prepare_cashback_link to actually earn cashback.

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