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

Annotations already flag destructiveHint=true and openWorldHint=true, so the safety profile is covered structurally. The description adds real behavioral context beyond that: the batch cap of 25 and the fact that the outcome is verified per-id ('Esito verificato per-id'), which tells the agent partial failures are reported individually.

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?

Four terse, front-loaded fragments with zero filler: purpose first, then each invocation mode, then the outcome guarantee. Every clause carries information an agent needs, and nothing is repeated from the schema.

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 mutation with no output schema, the description covers the value domain, the single/batch duality, the batch limit, and the per-id result semantics. The two-step preview/confirm workflow is only discoverable from the schema's confirm_id description, not the tool description, and reversibility of ARCHIVED is unstated.

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 50%, so the description must compensate, and it does for the core parameters: it documents keyword_id, state values, and the items batch structure with its max size. Critically, it clarifies that keyword_id+state and items are alternative modes rather than co-required, which the flat schema leaves ambiguous. It does not cover profile_id at all and leaves confirm_id/account_id to the schema.

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 lo stato'), resource ('keyword Sponsored Brands') and the exact value domain (ENABLED|PAUSED|ARCHIVED). The 'Sponsored Brands' scoping implicitly separates it from ads_update_sp_keyword_state and the state-vs-bid siblings (ads_update_sb_keyword_bid), but no sibling is named explicitly, so it falls short of a 5.

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?

The description lays out the two invocation shapes (SINGOLA: keyword_id + state; BATCH: items=[...], MAX 25), which tells the agent how to call it but not when to prefer this tool over ads_update_sp_keyword_state or ads_update_sb_keyword_bid. No prerequisites or when-not-to-use guidance are given.

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