crpt_set_key

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true), the description discloses the security-relevant behavior that the key goes into the chat transcript and requires explicit acknowledgment. It details post-execution behavior: 'On success the key is validated against the marketplace and the shop name is reported. Saved locally (chmod 600), never echoed back.' This adds significant context about file permissions and privacy.

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, front-loaded with the purpose, then a critical warning, alternative guidance, and parameter details. Each sentence serves a distinct function (purpose, safety, defaults, success behavior). The use of a warning emoji and bullet-like args formatting improves scannability without excessive length.

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 is thorough overall, covering safety, defaults, validation, and local persistence. An output schema exists, so return values are not required, but the description mentions the reported shop name. The only notable gap is the placeholder for required credential fields, which leaves an agent uncertain about what exactly to pass. Given that this is a security-sensitive operation, more specificity would improve completeness.

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 compensate. It thoroughly explains 'cabinet' (default behavior, fallback logic) and 'i_understand_key_goes_to_chat' (must be true). However, 'credentials' is only described as 'dict with the required fields ({fields})' – a placeholder that does not actually enumerate the required fields. This leaves the key parameter underspecified, though the description adds value by indicating a dict and implicit requirements.

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: 'Change / rotate the API key from chat (e.g. the old one expired or leaked).' It clearly differentiates this tool from sibling tools like crpt_list_cabinets or crpt_add_cabinet by its unique purpose of managing keys. The title 'CRPT set / rotate key' reinforces this, and the description adds the chat 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?

It explicitly provides when-not-to-use guidance: 'The safe, terminal-free alternative is the installer, where the key never enters chat.' It also advises on post-exposure handling: 'Use a scoped key and rotate it in the seller cabinet if it was exposed.' The description of the default cabinet behavior ('Default: the active one (so "my key expired" just works)') clarifies how to invoke it in a common scenario.

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