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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is known; the description usefully adds the confirmation gate and that the order line is derived from the visible Reference. It does not say what is destroyed or replaced (whether the marketplace-side address is overwritten irreversibly or whether the prior address is retained), which is the key open question for a destructiveHint=true tool, and it claims channelOAuthId is 'resolved internally' even though the schema marks it required.

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?

Three short sentences with the action and the confirmation gate front-loaded; nothing is padded. The closing clause 'Requires HGRApi Header channel / ChannelOAuthId resolved internally' is compressed to the point of ambiguity given the slash construction.

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?

With an output schema present and full parameter documentation, the description covers action, targeting, and the confirmation prerequisite adequately for an agent to call it. The remaining gap is outcome disclosure for a destructive write (what the prior address becomes) and the internal-resolution claim that conflicts with the required channelOAuthId parameter.

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%, so baseline is 3; the schema already explains body, confirmed, reference, and channelOAuthId including the hgr_list_channels source. The description's 'body: include shippingAddress only' framing echoes rather than extends the schema.

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 pair ('sets/corrects the shipping address for an order') and explains how the order is located ('resolved from the visible order Reference'), which an agent could not infer from the name alone. It does not differentiate from related siblings such as hgr_load_order_addresses or hgr_load_shipping_options, so a caller must guess whether those are prerequisites or alternatives.

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 confirmed=true' is an explicit invocation gate tied to the schema's confirmed parameter, which is real guidance. However, there is no when-not guidance and no named alternative, so an agent cannot tell from the description whether it should first read existing addresses via hgr_load_order_addresses before correcting one.

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