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

Annotations already declare readOnlyHint/idempotent/non-destructive, and the description adds meaningful context on top: nothing is persisted, validation is native, and the result is an exact before/after preview. It also implies the optimistic-concurrency contract (copy expectedRevision verbatim from a prior read) that annotations cannot express. It does not describe the shape of the preview, which matters since there is no output schema.

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?

Front-loaded with the precondition and the locking requirement, and every clause carries information. The telegraphic style ("Native validation and exact before/after preview") is terse to the point of being slightly cryptic, but there is 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 two-parameter tool with a deep oneOf schema, no output schema, and zero parameter descriptions, the definition covers the workflow and safety story well but leaves the agent without guidance on which setting variant to construct or what the preview returns. That is the remaining gap for correct invocation.

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 0%, so the description must carry parameter meaning. It does well on expectedRevision (must be copied exactly from a read) and on patch semantics ("omissions preserved" = partial update). However it says nothing about the `setting.kind` discriminator or the business vs. brand field families, leaving the largest part of the schema's structure unexplained.

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 conveys that this validates a patch against the current revision and returns an exact before/after preview with no persistence, which is a real verb+outcome. But it never names the resource precisely ("matching settings") and the tool name promises "business_model" while the schema also accepts brand patches, so an agent cannot fully tell what it is preparing without opening the schema.

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?

"After explicit request" gives a clear precondition, and "Human execution uses show_business_settings_approval with identical input" explicitly routes the agent to the correct sibling for the actual write. "No publication, send or reissue" adds an exclusions clause. It stops short of naming when-not-to-use beyond that one alternative.

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