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

Annotations declare destructiveHint=true, but the description adds crucial behavioral detail beyond that: Amazon rejects negative SB multipliers as of 15/6/2026 and the tool rejects them before calling Amazon; passing multipliers forces bid_optimization=false per Amazon's requirement; verified per-id and per-placement read-after-write; max 25 batch items. This is exactly the kind of enforcement/policy context annotations cannot 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 dense and information-packed, front-loaded with the core action and scope. Some clauses are long and could be split for readability, but every sentence carries operational value. Slightly overstuffed for a one-pass read, preventing a perfect score.

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 mutation tool with no output schema, the description covers every behavioral burden: destructive nature, two invocation modes, batch limit, Amazon policy constraints, confirmation flow implied by confirm_id schema, and the read-after-write verification. An agent has everything needed to invoke correctly. Neither schema nor annotations carry this load.

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 description coverage is 50%, so the schema documents some parameters (bid_optimization, placement, percentage, account_id, confirm_id, items). The description adds the enum of placement values with aliases (top, detail_page, home, other) and the positive-only constraint on percentage, plus the interplay between bid_optimization and multipliers. However, several parameters (daily_budget, state, campaign_id, patches structure) receive no extra semantic detail beyond what the schema already provides.

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 and resource: updates one or more EXISTING Sponsored Brands campaigns, covering budget, state, and bid optimization. Explicitly says it does NOT create new campaigns, distinguishing it from ads_create_sp_campaign and the S-family create tools.

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?

Rich when-to-use guidance: single mode (campaign_id + patches) vs batch mode (items, max 25). Explains the bid optimization workflow (multipliers vs keywords): to reduce spend on a placement, lower keyword/target bids and raise other placements. Names the sibling tools ads_update_sb_keyword_bid and ads_update_sb_target_bid as the alternative path.

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