wb_delete_method

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

Annotations already provide destructiveHint=true and readOnlyHint=false, so the description's job is lighter. It adds meaningful behavioral context: writes are irreversible, and nothing is sent unless both confirm_write and i_understand_this_modifies_data are true, and it documents the response/error envelope. This goes beyond the annotations without contradicting them.

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 and front-loaded with the destructive warning, followed by the API link, mandatory confirmation flags, a compact parameter list, and return format. The only weakness is redundancy: the two confirmation flags are stated both in the opening paragraph and again in the Args list. Still, every sentence earns its place.

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 generic destructive executor with six parameters, the description covers the core needs: what the tool does, where operation_ids come from, how to pass path/query/body values, the mandatory safety flags, and the return/error envelope. It does not mention authentication prerequisites or explicitly route to alternatives, but the output schema and annotations cover some of the remaining context.

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%, so the description must compensate, and it does. It lists all six parameters with useful meanings: operation_id comes from the catalog, path_values fill placeholders, confirm_write and i_understand_this_modifies_data must be true. Some entries like 'query: query-string parameters' and 'body: JSON request body' are thin, but the critical safety flags and catalog linkage are explained.

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 action ('Execute one DESTRUCTIVE endpoint') and clarifies the resource ('deletes or irreversibly changes data'), which clearly separates it from read-only or non-destructive write tools. It does not name a specific endpoint because it is a generic catalog-based executor, but the destructive framing and target API URL make the purpose understandable.

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 usage: use this tool when an operation_id from the Wildberries catalog is destructive, and it points to wb_search_methods for finding operation_ids. However, it does not explicitly contrast with sibling tools like wb_write_method, wb_call_method, or wb_delete_raw, nor does it state when not to use this tool. The guidance is clear but left largely to inference.

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