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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds the crucial upsert semantics: "The same name again changes that one," which the annotations cannot express. It also discloses the size-refusal behavior and what each call returns (names added and changed plus catalogue count). What it does not say is whether a same-name update merges or replaces existing fields, so destructive impact is still partly opaque.

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?

It is front-loaded with the core action and every clause carries information: batching, upsert, return shape, downstream consumers. The prose is a single run-on paragraph with chatty framing ("what it is"), and the closing get_setup sentence is borderline but does help verify results.

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 no output schema and a single nested array parameter, the description covers return values, size limits, retry behavior, and how the data is later consumed (catalogue for make_pictures, services on the Brand page). The remaining gap is update semantics against the destructive hint: whether re-sending a name overwrites or merges fields is not stated.

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 100%, so the nested product fields are already documented, and the baseline is 3. The description goes beyond the schema by explaining the deferred-picture workflow tied to picture_file_ids and by reinforcing that price is captured "as written" alongside the numeric amount, adding meaning the field descriptions only imply.

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 states the verb and the resource, though obliquely: "Adds what the business sells to the setup" is immediately unpacked as products and services with price, page, description, and pictures. It implicitly separates the tool from add_pictures (file ids come from there) and get_setup (reads back the catalogue), but never names a sibling as an explicit alternative.

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?

It gives real routing guidance: use file ids from add_pictures, or call add_pictures afterwards using the product's name, which resolves an ordering question an agent would otherwise guess at. Batching guidance ("send as many in one call as fit in one message... if a call is refused as too big, send fewer") is explicit. It stops short of naming when NOT to use it, e.g. removal via offering_remove.

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