Прямой вызов API Яндекс Директа

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

The description adds meaningful disclosures beyond the annotations: money values are passed in micro units without conversion ('Деньги — в микроединицах'), a data-representation gotcha that could silently corrupt bids; it also explains the write-confirmation gate (confirmWrite) for anything not get/has/check. The read/write semantics align consistently with readOnlyHint=false and destructiveHint=true. A small amount of additional color about side effects or response behavior would push this to 5.

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 dense sentences with zero fluff: one for the mechanism and example, one for the use case, one for data-format and safety semantics. Every sentence earns its place, and the most important differentiator (universal fallback) is front-loaded. This is exemplary conciseness, not under-specification.

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 an open-world, generic passthrough tool with no output schema, the description covers the critical ground: what it does, when to use it, how writes are gated, and the numeric-unit gotcha. Given its inherent universality (openWorldHint=true, so full behavioral documentation is impossible by design), this is appropriately complete. It could mention rate limits or the absence of an output schema, but those are minor given the passthrough 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?

With 100% schema coverage, the baseline is 3, and the description correctly avoids restating parameter definitions. It earns a 4 by enriching the meaning of what gets passed in params (unit semantics for money, the distinction between read and write call shapes) and by explaining when the confirmWrite flag is mandatory. The example format (service 'bidmodifiers', method 'get') also clarifies the expected shape of two parameters beyond their schema text.

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 states a specific verb and resource ('вызывает напрямую любой сервис или метод API Яндекс Директа v5') with a concrete example (service 'bidmodifiers', method 'get'). It explicitly frames itself as the universal fallback ('для сервисов, у которых нет отдельного инструмента'), which functionally distinguishes it from the many sibling wrappers. The role of 'generic passthrough vs. specialized siblings' is immediately clear.

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 explicitly conditions usage on the absence of a dedicated sibling tool ('Нужен для сервисов, у которых нет отдельного инструмента'), telling the agent when to select it over alternatives. It also prescribes the read vs. write usage path (get/has/check free; anything else requires confirmWrite=true). It falls just short of 5 by not enumerating concrete sibling names to prefer, and its own 'bidmodifiers' example slightly conflicts with the guidance, since bidmodifier siblings already exist.

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