sbis_set_key

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

Annotations only cover idempotency and destructive potential, but the description adds much more: the key goes into the chat transcript, a confirm flag is required, the key is validated and saved locally with chmod 600, never echoed back, and the shop name is reported on success. No contradiction with annotations exists.

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: purpose, warning, args, and success behavior. It stays focused and front-loads the most important caveat. The only blemish is the unresolved '{fields}' placeholder, which makes it slightly less polished, but it is not verbose or redundant.

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 the hazard, the required permission flag, cabinet fallback logic, and post-success validation. However, it omits the actual required fields for the credentials object, which is essential since the schema provides no property definitions and coverage is 0%. This prevents an agent from constructing a valid call without further information.

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 must carry the parameter semantics. It explains cabinet defaulting and the i_understand flag, but credentials is only described as 'dict with the required fields ({fields})' – a placeholder rather than actual field names. This is a critical gap for correct invocation.

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 verb and resource: 'Change / rotate the API key from chat', with a concrete use case ('old one expired or leaked'). This clearly distinguishes it from all sibling tools, none of which handle key rotation.

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 says when to use the tool (key expired or leaked), warns about the key entering the chat transcript, and names a safer alternative (the installer). It also advises using a scoped key and rotating in the seller cabinet if exposed, leaving no doubt about selection and precautions.

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