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

Annotations already declare readOnly=false, destructive=false, idempotent=true, so the mutation safety profile is covered. The description adds genuinely non-structured context: who the real caller is (in-chat cards, not the agent), which is the single most important behavioral fact about this tool. It stops short of saying whether a save replaces prior picks or how failures 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 short sentences, front-loaded with the scoping constraint and immediately followed by the prohibition and the read alternative. No filler or restated schema.

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 tool agents should generally not call, this fully answers the operative question ('should I call this? no, use get_owner_picks'). No output schema exists, so no return-value explanation is owed; only edge behavior on save (overwrite semantics, error handling) is unstated.

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 100% and each parameter already carries a description, an example object, and a format pattern for chat_token. The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

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 makes clear this writes the human's selections on behalf of the shop-window cards, and the title supplies the verb ('Record'). It distinguishes the write path from get_owner_picks, though it never plainly states 'stores the ticked items' — the action is inferred from the calling context rather than asserted.

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?

Explicit when-to-use (AgentMart shop window, when your human presses Send), explicit when-not (Agents: never call it yourself), and an explicit alternative for the read case (get_owner_picks). Nothing is left to inference.

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