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

Annotations already declare destructiveHint=true and the write nature. The description adds useful context: batch limit of MAX 25 and per-id read-after-write verification. However, it omits the preview/confirm (confirm_id) two-step execution flow visible in the schema, which is a notable behavioral trait for a destructive write.

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?

Front-loaded with purpose, then usage rationale, then the two invocation shapes and the batch cap. Dense and efficient, though the ALL-CAPS emphasis on multiple terms is slightly noisy rather than informative.

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 6-parameter, zero-required, destructive write tool with no output schema, the description covers modes and verification but leaves the confirm_id preview-execute contract unexplained, which an agent needs to invoke it 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 50%. The description meaningfully explains keyword_id (source: ads_list_sb_keywords), bid, and the items batch shape with a max, but says nothing about account_id, profile_id, or the confirm_id preview token covered only in 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 il BID) and resource (keyword Sponsored Brands), and explicitly covers both single and batch modes. It distinguishes itself from the many sibling bid/state tools by naming the SB keyword resource and its scope.

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?

Explains when to reach for it (the lever to optimize an underperforming SB campaign 'instead of turning it off or throttling budget'), implying the alternative of ads_update_sb_keyword_state. It also routes the agent to ads_list_sb_keywords for obtaining keyword_id, but does not name the state-update sibling explicitly.

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