hh_add_cabinet

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

Goes well beyond the annotations: it discloses the security consequence (key lands in the chat transcript), the required acknowledgement flag, the on-disk destination and permissions (~/.marketplace-mcp/cabinets.json, chmod 600), and that the value is never echoed back. That is exactly the extra behavioral context the readOnly/idempotent hints cannot convey.

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?

Front-loads the action and the warning, then breaks parameters into a readable Args block — every sentence earns its place. The literal escaped newlines and doubled braces from the raw template add minor noise, but the content density is high.

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 write tool with a nested credentials object, a safety gate, and no parameter documentation in the schema, the description covers inputs, side effects, storage location and the safe alternative. With an output schema present, no return-value prose is needed, and nothing an agent requires to call this correctly is missing.

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 coverage is 0%, so the description carries the full burden and does: it defines the credentials object shape with concrete per-service examples (Ozon client_id/api_key, WB token), and explains that name is optional with a non-obvious fallback to the marketplace shop name or 'main'. The usually-inscrutable boolean is also explained as a hard gate.

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?

Specific verb+resource ('add or update a cabinet — a named set of API credentials') with an explicit scope qualifier ('from chat'), which cleanly separates it from siblings like hh_set_key, hh_list_cabinets, hh_use_cabinet and hh_remove_cabinet. An agent can route correctly without opening any schema.

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 gives a clear conditional ('from chat') and names the preferred alternative path — the installer (install.py / double-click) where the key never enters the chat — which is strong when-to-use guidance. It does not, however, contrast with the closest sibling hh_set_key, so the agent still has to infer which key-writing tool to pick in a non-chat context.

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