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

The description carries behavior no annotation can express: calling the tool applies nothing, it returns a preview of the diff plus a confirmation link, and the real change requires the merchant on that page. This resolves the tension with readOnlyHint=false (the call stages a pending change rather than altering live settings) instead of contradicting it.

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 tight sentences, front-loaded with purpose, then the units caveat, then the critical no-op/confirmation behavior. Nothing is padded, though the units sentence sits slightly apart from the confirmation-flow message it precedes.

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 7-parameter tool with nested objects, enums, and no output schema, the description supplies the two things structured data cannot: the deferred-confirmation lifecycle and a sketch of the return (preview of changes + confirmation link). Parameters themselves are fully covered by 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 description coverage is 100% and the nested structuredData fields are thoroughly documented inline, so the schema does the heavy lifting. The description only adds a units reminder (money in integer minor units / cents), which restates what the schema already says for returns.fee.

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 opens with a concrete verb+resource ("Set how the shop describes itself to search engines"), so the operation and its domain are unambiguous. It does not explicitly route against siblings such as settings_*, branding_set, or shop_state, but no sibling shares the SEO resource, so the boundary is inferable 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?

Usage is implied by the resource (configure the shop's search-engine metadata), and the description usefully notes that only the merchant can actually apply the change. However, it never states when to reach for seo_set versus adjacent settings tools, nor any preconditions or exclusions.

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