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

Annotations already flag destructiveHint=true and openWorldHint=true, so the safety bar is lower, and the description still adds real value: 'Rebuild' discloses that the existing partition tree is replaced rather than appended to, and the confirmation policy for bid increases / un-exclusions is spelled out beyond what annotations provide. It stops short of saying what happens to previously excluded values or how partial failures are handled.

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?

Two sentences, front-loaded with the action and the dimension set, and every clause carries meaning — no filler. The density makes it slightly run-on, requiring a second read to parse the value/bid/exclude triple, which keeps it off a 5.

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 8-parameter mutation with no output schema, the description explains the operation's shape but omits the bid unit/currency format and does not clarify whether omitted existing product groups are discarded on rebuild or merely left untouched. These are the details an agent most needs before invoking a destructive call, even with the confirm and dry_run fields present in 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?

With only 38% schema description coverage across 8 parameters, the description does genuine compensating work: it explains that each entry in values takes either a bid or an exclude flag, and it names the catch-all semantics of others_bid and exclude_others ('a bid (or exclusion) for everything else'). Only ad_group_id and account go unmentioned, and those are self-evident.

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 ('Rebuild a Shopping ad group's product groups') and immediately enumerates the permitted partitioning dimensions (brand, product type, item ID, custom label, condition), which maps directly to the dimension enum. No sibling tool in the list handles Shopping product group partitioning, so this 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?

It gives one concrete procedural rule — 'Higher bids or un-excluding need confirmation' — which tells the agent when the confirm gate is required. However, it never states prerequisites (Shopping campaign requirement, Merchant Center link) or when to prefer this over related tools like google_ads_pmax_listing_filters or google_ads_update_ad_group; usage must be inferred from the verb 'Rebuild'.

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