diadoc_add_cabinet

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

The description surfaces security-sensitive behavior beyond the annotations: the key is placed in the chat transcript, it requires an acknowledgment flag, and the cabinet is saved to a local file with chmod 600 and never echoed. Annotations already declare the tool mutable (readOnlyHint=false) and idempotent, so this extra context elevates transparency.

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 usefully structured with a warning, a bullet list-like argument breakdown, and an outcome line. It is a little longer than required, but every sentence earns its place by documenting the risk, the parameters, and the safe storage behavior.

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?

Given the output schema exists, the description doesn't need to explain return values. It covers the side effects (file, permissions, chat transcript), parameter nuances, and the required consent flag. Some edge cases like what happens if the cabinet already exists are only implied by 'Add or update', but the overall context is solid.

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?

Despite 0% schema-description coverage, the description provides concrete parameter semantics: `credentials` is detailed with Ozan and WB examples, `name` is described as optional with fallback logic ('named after the real shop name... falls back to "main"'), and `i_understand_key_goes_to_chat` is clearly tied to the chat key risk. This compensates fully for the schema's lack of inline descriptions.

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 a verb and resource: 'Add or update a cabinet (a named set of API credentials), from chat.' It gives the object a concrete meaning and scopes the action to chat. It doesn't explicitly contrast with `diadoc_set_key` or other siblings, but the resource is clearly differentiated enough for an agent to guess when it applies.

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 mentions a safe alternative: 'The terminal-free safe alternative is the installer...' and implies this tool should be used only when the user accepts the key going into chat. It also requires (via parameter) an acknowledgment flag. It doesn't mention all siblings like `diadoc_use_cabinet` or `diadoc_remove_cabinet`, but the core when-to-use/when-not-to-use guidance is present.

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