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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation risk is covered. The description adds only two behavioral facts beyond that: the hard batch cap of 25 and per-id result verification ('Esito verificato per-id'). It is silent on the preview/confirm_id write gating and on the effective irreversibility of ARCHIVED.

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?

Telegraphic and front-loaded: purpose first, then the two calling modes, then the batch cap and the verification note. No filler sentences, though the shorthand style trades some readability for density.

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 write tool with 6 parameters and 0 required ones, the omission of the preview -> confirm_id workflow is a meaningful gap in the description itself, and the optional account_id/profile_id scoping is left to the schema. No output schema exists, so the per-id result note is a helpful partial substitute.

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 50%, so half the parameters carry their own documentation. The description's real added value is the single-vs-batch parameter pairing, which the flat schema cannot express. It says nothing about account_id, profile_id, or the confirm_id confirmation token.

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 (Aggiorna stato) and a precise resource (SB product target), and the enum of resulting states makes the effect unambiguous. It implicitly separates itself from ads_update_sb_target_bid and ads_update_sp_target_state by naming 'stato' and 'Sponsored Brands', but never explicitly names those siblings.

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 clearly tells the agent which shapes select which mode: SINGOLA = target_id + state, BATCH = items=[{target_id, state}] with MAX 25, so parameter selection is unambiguous. It stops short of saying when to prefer this over ads_delete_sp_targets or the bid-update sibling, and gives no exclusions.

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