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

With annotations already declaring readOnlyHint=false and destructiveHint=true, the description adds rich behavioral context: audience segments can only raise bids, max 10 segments, placement multipliers are reread and preserved, preview writes nothing, confirm writes and is verified by rereading. This goes well beyond the safety profile that annotations provide.

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 front-loaded with purpose, then options, constraints, and flow. It is dense but justified by the complexity of a mutation tool with a preview-confirm workflow. Some all-caps emphasis and repetition of confirm details slightly reduce conciseness.

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 complex destructive mutation tool with no output schema, the description covers the confirmation flow, merge behavior, bid constraints, and practical preconditions. It misses an explanation of profile_id and campaign_id, but otherwise provides enough context to invoke the tool correctly.

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 75%, and the description adds substantial meaning beyond the schema: percentage is an integer 0–900 that only increases bids, set adds/modifies, remove deletes, clear_all zeroes all, and confirm triggers the actual write. However, parameters such as profile_id and campaign_id remain unexplained in both the schema and the description.

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 names a specific verb (imposta/moltiplicatori) and resource (segmenti di pubblico di una campagna Sponsored Products), and explicitly identifies the underlying API path dynamicBidding.shopperCohortBidding. It distinguishes the four operations (set, remove, clear_all) and clarifies that it is not a generic campaign update, unlike siblings such as ads_update_sp_campaign.

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 a clear usage flow (preview without confirm, then confirm=true) and a practical when-to-use rule (only on campaigns with ACoS within target, over 14–30 days). It also points to ads_list_sp_audiences for audience_id, but it does not name alternative sibling tools for related bidding changes, so it falls short of full when/when-not/alternatives guidance.

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