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

Adds substantial behavior beyond the annotations: preview-by-default with nothing applied, merge-per-attribute semantics so one field can be fixed per call, precedence over the store's shared rule, conflict protection via the revision token, and the fact that changes only reach Google on the next generation run. The destructiveHint=true annotation is reconciled by the preview gate, not contradicted.

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 purpose and ordered sensibly from payload shape to merge semantics to the preview/confirm gate. It is on the long side, and the preview behavior is restated in both the description and the confirm parameter's schema text, which is mild redundancy for a safety-critical point.

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 nested-object mutation tool with an output schema present, the description covers everything an agent needs: payload shape, merge/drop semantics, scoping and precedence, the two-phase confirm flow, the revision guard, and downstream propagation timing. No return-format explanation is needed.

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 already 100%, so the schema itself documents confirm and revision. The description still adds meaning the schema does not carry: that a null attribute value drops the mapping and reverts it to the smart default, and that mappings are feed-scoped and outrank shared rules. That is real added value above the 3 baseline.

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?

Opens with a specific verb and resource ('Update a feed's attribute settings') and immediately characterizes the payload shape ('PARTIAL settings object mirroring the tab shape from get_feed'). It is clearly distinguishable from siblings like get_feed, list_feeds, and the set_product_override family.

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 an explicit ordered workflow (preview first, show merchant, then call again with confirm: true) plus two named prerequisites: call get_mapping_schema before writing a mapping, and fetch the tab shape from get_feed. It also states the exact condition for dropping a mapping (pass null).

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