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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial context beyond them: every item ships with its evidence and the risk screen a draft would get, the draft is a ready {tool, args} payload, filing requires seller consent, and follow_up_on represents the 14-day verdict day. That is real behavioral detail an agent needs to orchestrate the follow-through.

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 the highest-value claim ('What to change in Sponsored Products now, and why') and every clause is actionable rather than filler. The first sentence is a long enumeration that demands careful reading, which keeps it just short of 5, but nothing is redundant.

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?

With no output schema, the description must convey the return shape, and it does: a list of items, each with evidence, risk screen, and a {tool, args} draft, plus a follow_up_on field. Combined with the usage and workflow guidance, an agent has everything needed to call it and act on the result.

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 100% and both parameters are optional with their own descriptions, so the schema carries the load. The description adds nothing about `account` or `marketplace_id` (e.g. agency multi-account behaviour or marketplace scoping), so the baseline 3 applies.

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?

Names the exact resource (Sponsored Products ads) and enumerates the concrete change types it returns: break-even-CPC bid cuts/raises, negatives, EXACT keyword additions, budget changes, placement adjustments, out-of-stock pausing. This clearly separates it from data-only siblings like get_ads_targets or get_ads_search_terms, and from get_amazon_bid_recommendations which is Amazon's own feed rather than measured break-even analysis.

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?

Gives explicit trigger phrases ('what should I change in my ads', 'optimise my PPC', 'audit my campaigns') and states the downstream workflow: file each item with its `draft` tool ONLY after the seller agrees, then offer schedule_follow_up on `follow_up_on`. It also rules out mutation ('Reading this changes nothing'), so the agent knows this tool alone writes nothing.

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