Произвольный вызов API Яндекс Доставки

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

Annotations already flag destructive/read-only nature, but the description adds important behavioral details: the retry policy (5xx/network errors only for GET) and host/path conventions for each contour. This goes beyond the structured 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?

The description is compact, using only two sentences to convey purpose, param roles, and cautions. Every sentence is informative with no irrelevant filler.

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 generic raw-request tool with 5 params and no output schema, the description covers purpose, usage, parameter roles, and security cautions. It does not mention auth prerequisites or error response structure, but these are not strictly required given the fallback nature.

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?

Although the schema covers 100% of parameters with descriptions, the description enriches these by explaining the mapping of `contour` to host and path prefix patterns, and clarifies that `body` is sent as JSON. This adds meaning beyond the schema.

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 it is a fallback tool for direct calls to any B2B API method not covered by dedicated tools, with a specific list of example endpoints. This clearly distinguishes it from siblings like express_create_claim or platform_get_request.

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?

Explicitly states 'for endpoints without a dedicated tool' and labels itself as a fallback, giving clear when-to-use guidance. It also cautions about modifying operations and the GET-only retry policy, which helps avoid misuse.

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