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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is known. The description earns credit by adding context annotations don't carry: that actions hit the owner's real Komers account, which concrete operations count as changes (create/cancel orders, update stock, send messages), and the confirm-first protocol. It still omits how invalid tool names or bad arguments surface.

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?

Two tight sentences, front-loaded with the action and followed by the destructive-action warning. Nothing is redundant. It is somewhat terse for the amount of ambiguity a generic dispatcher carries, but the wording itself is efficient.

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 catch-all dispatcher with two parameters, zero schema coverage, no output schema and open-world behavior, the description leaves out the two things an agent most needs: the discovery step (call komers_tools to get valid names) and the argument contract (arguments must conform to the target tool's schema). The confirmation rule is the only operational detail supplied.

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 description coverage is 0%, so the description must compensate and largely doesn't. It clarifies that `tool` is a name taken from komers_tools, which is genuinely useful, but `arguments` — a free-form nested object that must match the target tool's own schema — is left entirely unexplained. An agent gets no guidance on how to shape it or what happens to unknown fields.

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 and resource: run one tool from komers_tools with its arguments. Sibling disambiguation is partial but real — it points the agent at the komers_tools catalog as the source of valid tool names, which separates it from dedicated siblings like list_komers_products or komers_status. What it cannot convey (which tools exist) is inherent to a dispatcher, not a description failure.

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 condition (running a Komers tool for the owner) and a strong precondition for mutating calls: confirm with the owner first. It does not state that komers_tools should be called first to discover valid names, nor does it say when to prefer the purpose-built siblings over this generic dispatcher.

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