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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds valuable behavioral context beyond annotations: it specifies the returned fields (targetId, state, and bid if set) and provides a mapping from expression.type to UI group names. It does not mention pagination or rate limits, but the added return and mapping details are substantial.

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?

The description is dense but front-loads the core purpose and then provides necessary details like the AUTO group mapping and bid-change workflow. Some sentences are long and could be structured more clearly, but every part appears to serve a purpose and nothing is obviously redundant.

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 read-only list tool with no output schema, the description does a good job explaining the return fields (targetId, state, bid) and how to use the result for a subsequent bid update. It also warns against creating AUTO targets. However, it leaves some contextual gaps around filtering parameters and pagination, which are not covered by the schema or annotations.

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 only 20% (only account_id has a description), so the description must compensate for the other four parameters. It partially explains campaign_id by implying it is used to retrieve AUTO groups, but profile_id, ad_group_id, and state_filter are completely unexplained, leaving significant gaps for an agent trying to invoke the tool correctly.

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 clearly states it lists SP targeting clauses and distinguishes between MANUAL targets (ASIN/category) and the 4 AUTO groups. It also names the sibling update tool and warns against using create tools for AUTO, making it easy to tell apart from siblings like ads_create_sp_product_targets or ads_update_sp_target_bid.

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 explicitly says when to use this tool (to get targetId for an AUTO group bid change) and when not to use alternatives (do not use ads_create_* on AUTO because targets already exist). It also provides a concrete workflow: call this tool with campaign_id, take targetId, then call ads_update_sp_target_bid.

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