Возвраты

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by listing accepted date formats ('вчера', '-7d', absolute dates), but it does not disclose output shape, pagination behavior, or scope limitations.

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?

Two compact sentences: the first states purpose, the second gives concrete date examples. There is no filler, though the date list is slightly telegraphic.

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 5-parameter, no-output-schema read tool, this definition is enough to get started, but an agent would have to guess at limit and filial_code semantics and cannot anticipate the response shape. The rich annotations and clear purpose keep it from being inadequate.

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?

The schema already documents end, begin, and query, but limit and filial_code have no descriptions, so 40% of parameters are undocumented. The date-format note helps interpret begin/end, but the description does not compensate fully for the missing parameter meaning.

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 as goods returns over a period and specifies the concrete questions it answers: 'what was returned' and 'how many returns a customer has'. It does not explicitly contrast with siblings like smartup_sales or smartup_orders, but the subject matter is specific enough to distinguish it.

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 implies the tool is for return-related analytical queries and gives useful date syntax, so an agent can infer when it is appropriate. However, it provides no explicit guidance about when to prefer a sibling tool or when not to use this one, which matters given the large sibling family.

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