Update loyalty settings

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

Annotations already declare destructive=true, idempotent=true and openWorld=true, so safety is covered. The description adds non-obvious context the annotations cannot — that StreamElements leaves the body undocumented and that the input must mirror the shape returned by loyalty_get_settings — which is exactly the risk information an agent needs for a destructive write to an undocumented API.

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, front-loaded with the action, followed by the undocumented-body caveat and the concrete shape instruction. No filler.

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 destructive, undocumented-body mutation with full schema coverage and no output schema, this covers the essentials. The one notable omission is whether sending a partial document replaces or merges with existing settings, which matters given destructiveHint=true.

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 the baseline is 3, and the description goes beyond it by explaining both the required `settings` payload's lineage (it is the loyalty_get_settings document, at least its `loyalty` object, with edits applied) and how it is sourced. It does not document the optional `channel` parameter, but the schema does.

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 ('Update the channel's loyalty settings'), so an agent can immediately tell this is the loyalty write path. It does not explicitly contrast itself with similarly-named siblings like filters_update_settings or sessions_update_settings, though the loyalty domain is unambiguous.

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 workflow: read the current document via loyalty_get_settings and send it back with changes applied, which effectively tells the agent when and how to invoke this. It stops short of naming when-not to use it or listing alternative settings endpoints.

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