wb_promotions_audit

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

With no annotations provided, the description carries the full disclosure burden and delivers: it states the API's rate limit ('Auto-throttled to 10 req/6 s') and a meaningful data-availability limitation ('For auto-promos WB hides the item list'). It doesn't explicitly confirm read-only behavior or describe error modes, but 'audit' plus these disclosed constraints gives a solid operational picture.

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, each carrying distinct information: purpose, limitation-plus-alternative, and rate limit, with the core purpose front-loaded. The '[P0]' prefix and the Russian endpoint parenthetical '(аудит акций)' are minor extras that add identification context without bloating the description.

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 no output schema and no annotations, the description covers the essentials: what it computes, its key limitation, its rate limit, and where to route for related price control. The main gap is the absence of any detail about the response shape, which the description cannot fully compensate for without an output schema, but this is minor for a read-oriented audit tool.

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 — the schema already documents all four parameters with descriptions. The description adds marginal context to only_auto by explaining the auto-promo item-hiding behavior it selects, but adds nothing about start/end or max_promotions beyond what the schema already states.

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: 'Participation audit' over promotions, and defines the output precisely — 'which promotions already hold my goods and the price effect (price→planPrice, % drop).' This clearly distinguishes it from sibling tools like wb_promotions_list, wb_promotions_details, and wb_promotions_products, which list or manage promotions but do not audit participation with price effects.

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?

It provides explicit routing for the auto-promo case: when WB hides the item list (nomenclaturesAvailable=false), 'control prices via wb_prices_list/wb_prices_quarantine,' which is a concrete when-not/alternative. The primary when-to-use is strongly implied by the audit purpose, but the description never explicitly contrasts itself with the promotion-list siblings, so the main use case is left slightly to inference.

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