Propose: add order note

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

The annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true; the description adds real value on top by disclosing that notes default to private, can optionally notify the customer, and are gated behind human approval rather than applied immediately. It does not discuss whether re-proposing the same note creates a duplicate proposal, which matters given idempotentHint=false.

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 action and followed by the approval constraint; every clause carries information and nothing is padded.

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 non-destructive proposal tool with no output schema, the description covers what is created, its visibility default, and the approval gate an agent must expect. It leaves open what the tool returns (a proposal identifier for later apply_proposal) and any note-length constraint, but those are minor against the 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 50%: only reason and customer_note carry schema descriptions. The description's '(private by default, or visible to the customer)' glosses the customer_note flag and its default, adding meaning beyond the terse 'true = the customer is notified', but order_id and note receive no explanation in either the schema or the description. That is adequate but not compensating for the coverage gap.

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 names a specific verb and resource ('Propose adding a note to an order') and scopes it with the private-vs-customer-visible distinction, which clearly separates it from sibling proposals such as propose_order_status or propose_refund. It stops short of explicitly naming those siblings, so differentiation is implied by the resource rather than stated.

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?

'Requires human approval' gives the agent the key workflow context: this tool stages a change rather than committing it, so a separate apply step follows. It does not mention the apply_proposal/list_proposals siblings by name or state when a note should not be proposed, so there are no explicit exclusions.

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