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

Annotations already establish readOnly/idempotent/non-destructive behavior. The description adds practical behavior beyond that: 'Returns a shortlist with final customer prices (delivery included) and delivery days,' 'Paginate with cursor,' and the operational requirement to ask for the country first. No contradiction with annotations.

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 sentences, front-loaded with purpose, then filters and output, then a clear operational note. Every sentence adds necessary context and the most important constraint (country required, ask for it first) is last but emphasized.

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?

Given the output schema and strong parameter schema, the description covers the essential workflow: required country, filters, return values, pagination, and customer-facing context. It doesn't detail every parameter, potential errors, or fallback behavior, but those are largely covered by the schemas and its scope is appropriate.

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 89%, so most parameters are already documented. The description adds minimal extra semantics by summarizing filter categories (free text, occasion, budget, needed-by date, country) and clarifying prices are in minor units via the schema. It doesn't deeply supplement the schema, but it doesn't need to given high coverage.

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 states the tool's action ('Find gifts that can be delivered to a destination country') and distinguishes it from siblings by mentioning exactly what it returns: a shortlist with customer prices, delivery included, and delivery days. This makes it distinct from check_delivery, get_gift_details, and the order-related tools.

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 description gives clear context: it applies when searching for deliverable gifts, with optional filters and pagination, and explicitly instructs that country is required and should be asked for first. It doesn't explicitly name alternatives or state when not to use this tool, but the sibling set and output make the primary intent obvious.

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