diadoc_add_cabinet

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

Adds substantial behavior beyond the annotations: the key is written into the chat transcript, a required consent flag gates the call, the result is persisted to ~/.marketplace-mcp/cabinets.json with chmod 600, and the value is never echoed. It also discloses side effects the annotations don't cover — the name falls back to the real shop name fetched from the marketplace, then to 'main'.

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 warning is front-loaded before the Args block, and each section earns its place: safety notice, parameter semantics, storage location. The unrendered brace placeholders and a couple of redundant restatements (the consent flag appears in both the warning and the Args) cost it a point.

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 3-parameter mutation tool with nested objects and an output schema, this covers what the schema cannot: consent gating, where the secret is written, that it is not echoed, and how the cabinet gets named. Return values are correctly left to the output schema.

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 full burden and mostly succeeds: it documents the per-service credential shape with concrete examples (Ozon client_id/api_key, WB token), the optional name and its fallback chain, and the mandatory consent flag. The literal unrendered template markers ('{fields}', '{{"client_id"...}}') are a defect that leaves the exact required-field list ambiguous.

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?

States a specific verb+resource ('Add or update a cabinet') and immediately defines what a cabinet is (a named set of API credentials), which cleanly separates it from diadoc_list_cabinets, diadoc_remove_cabinet, and diadoc_use_cabinet. The only friction is the naming mismatch: the tool is prefixed diadoc_ and sits among Diadoc document tools, while the body talks about Ozon/WB marketplace credentials, which could momentarily confuse selection.

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?

Gives a clear use context ('from chat') and an explicit when-not with a named alternative: 'the safe alternative is the installer (install.py / double-click), where the key never enters chat.' That is genuine routing guidance. It stops short of contrasting with the other credential-adjacent siblings (diadoc_set_key, diadoc_use_cabinet), so the agent still has to infer which key-entry path applies.

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