ozon_perf_fetch_all

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

Annotations provide readOnlyHint=true and openWorldHint=true, so the description does not need to restate safety. It adds valuable behavioral detail: auto-pagination, handling of multiple cursor styles, automatic array path detection, a max_items cap for context protection, and the exact return JSON structure including truncated flag. It also notes that cursor fields are managed by the tool. This exceeds what annotations convey and contradicts nothing.

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 well-structured: a concise two-sentence intro stating the core behavior and supported styles, followed by a bulleted Args list that maps directly to parameters. It is front-loaded with the main purpose and every sentence contributes to usability. There is no fluff or repetition, and the format is easy to scan.

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 7 parameters and an output schema, the description covers all essential aspects: what it does, how it handles pagination, how to specify the endpoint and parameters, the return format, and the truncation behavior. It also mentions defaults and overrides. Nothing critical is missing for an agent to correctly invoke the tool, and the presence of an output schema makes the listed return keys redundant but harmless.

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 0% schema description coverage, the description carries the full burden of explaining parameters. The Args section gives each parameter a purpose: operation_id as a read endpoint, query/body/path_values as base parameters with cursor fields managed, items_path as an override, limit as page size, max_items as a hard cap. This adds meaning far beyond the schema's type-only definitions, enabling an agent to understand how to populate each parameter 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 clearly states a specific verb and resource: 'Auto-paginate a read endpoint and return every row in one response.' It also enumerates the pagination styles handled (offset, last_id, cursor, page, lastChangeDate), which distinguishes it from sibling fetch_all tools for other platforms. This is unambiguous and action-oriented.

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 it is for read endpoints and auto-pagination, but it does not explicitly say when to prefer this over alternatives like call_method or other fetch_all variants. It mentions 'a read endpoint from the catalog' and the array path is taken automatically, but no explicit exclusions or comparisons with siblings are given. The platform context (Ozon Performance) is inferred from the name and the mention of Ozon v4/v5, but not stated directly.

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