ozon_fetch_all

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

The description discloses several behavioral traits: automatic pagination (cursor fields handled), max_items hard cap with truncation result, raw responses returned, and path/depth handling. However, it doesn't reveal whether the tool follows API rate limits, retries, or handles auth issues — but the annotation readOnlyHint=true and openWorldHint=true are consistent (read-only, may hit unknown endpoints). No contradiction. Could mention error behavior on non-paginated endpoints, but solid.

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 organized in a tight paragraph followed by a parameter list. It front-loads the key behavior (auto-paginate, return everything, capped). A couple of phrases are slightly redundant (e.g., 'read endpoint' is repeated, return shape is stated twice), but it's dense and scannable.

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 pagination wrapper tool, the description covers the essential invocation context: which endpoints are valid, what to pass, what comes back, and the truncation behavior. It doesn't exhaustively document every error case or authentication assumptions, but no output schema is provided, so disclosing the return envelope is important and it does. The presence of many sibling fetch_all tools (wb_fetch_all, ym_fetch_all, avito_fetch_all) makes the Ozon-specific read-endpoint framing adequate.

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_description_coverage is 0%, but the description explains every parameter's role: operation_id is the read endpoint to target, query/body/path_values are base parameters, cursor_fields are ignored/overwritten, limit and max_items control pagination, items_path is the array location. It adds semantics the raw schema does not convey (e.g., cursor fields are managed; items_path has heuristic default), compensating well for the 0% schema coverage.

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: "fetch all pages" / "list ALL calls in date range" pattern is replaced here with a clear statement that this tool returns every row from a paginated read endpoint in one response. It distinguishes itself from siblings like ozon_call_method, ozon_call_raw, ozon_fetch_all, and wb_fetch_all by saying it is the pagination-encompassing fetch-all variant for Ozon, and its name itself clearly pairs with the Ozon catalog context.

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 states when to use it: for read endpoints from the catalog that return arrays. It mentions that cursor fields are managed automatically them, warns the agent about the max_items cap, and explicitly says the tool returns raw API data — so the agent knows not to use it when processing or transformation is needed.

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