Создать объявление (banner)

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

The key behavioral disclosure is that content, textblocks, and urls 'отправляются как есть' (are sent as-is) with no transformation, and that the exact structure depends on the ad format per VK Ads documentation. This adds meaningful insight beyond the annotations, telling the agent the tool is a thin pass-through and that format-specific correctness lives in external docs.

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 with no filler: the first states the core action, the second maps the key structures to their roles, and the third sets expectations about pass-through and external documentation. Every sentence earns its place and the most important information is front-loaded.

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 tool with 6 parameters, nested objects, an open-world hint, and no output schema, the description is reasonably complete: it covers the action, the parameter roles, the pass-through behavior, and where to find exact shapes. It does not mention the response format or error behavior, but the explicit pointer to the VK Ads documentation compensates for the open-ended structures.

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 100%, so the baseline is 3, and the schema already provides concrete examples for content, urls, and textblocks. The description adds value on top by mapping each structure to its semantic role (creative media, ad texts, links) and by stating all of them are forwarded verbatim, which helps an agent fill them correctly.

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 opens with a specific verb-resource pair ('Создаёт объявление' – creates an ad) and scopes it precisely to 'внутри группы объявлений' (inside an ad group). This clearly distinguishes it from siblings like list_banners, update_banner, and banner_action without needing to open their schemas.

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 clearly signals the placement context: a banner is created within an ad group, which aligns with the required adGroupId parameter. However, it does not explicitly name alternatives or state when not to use it (e.g., 'to modify an existing banner, use update_banner'), so it stops short of a full 5.

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