wb_set_key

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

The description thoroughly discloses behavioral traits beyond annotations. It warns that the key enters the chat transcript, requires explicit acknowledgment, explains the validation against the marketplace, local storage with chmod 600 permissions, and states that the key is never echoed back. These details add significant security-context and operational behavior that annotations alone do not provide. No contradiction with annotations is present.

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 concise and well-structured. It leads with the purpose, then the critical warning and prerequisite, followed by parameter explanations and outcome. Each sentence adds distinct value; no filler or redundancy. The use of a warning emoji and clear sections makes it easy for an agent to parse quickly.

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?

The description covers all key aspects: the action, prerequisites, default behavior for `cabinet`, security consequences, expected outcome (validation and shop name reporting), and local persistence details. For a tool of this complexity (3 params, nested objects, output schema), the description is comprehensive and leaves no critical ambiguity for the agent to call it correctly.

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?

The description adds useful meaning to parameters: it explains the `cabinet` default logic (active cabinet, fallback to shop name, else 'main') and the `i_understand_key_goes_to_chat` requirement. However, the `credentials` parameter is only described as 'dict with the required fields ({fields})' – the '{fields}' placeholder is not resolved, so the actual required fields are not enumerated. Given the schema has 0% description coverage, the description partially compensates but leaves a gap for the credentials structure.

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 the tool's purpose: 'Change / rotate the API key from chat (e.g. the old one expired or leaked).' It specifies the exact action (change/rotate) on a specific resource (API key) and gives a concrete use case. It is easily distinguished from sibling tools like wb_add_cabinet or wb_list_cabinets, and from marketplace-specific variants like ozon_set_key.

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 explicitly states when to use the tool (key expired or leaked) and provides a clear warning about key exposure in chat, requiring the i_understand_key_goes_to_chat flag. It also names an alternative approach (the installer) for cases where the user wants to avoid key exposure in chat, and recommends using scoped keys and rotation in the seller cabinet. This fully guides the agent on when to use this tool versus alternatives.

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