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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds real behavioral value beyond that: the keyword-vs-product exclusivity rule per ad group and the specific otherError failure mode. It does not mention the two-step preview/confirm flow, but that lives in the confirm_id schema description.

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 action, then the constraint, then the payload shape - a sensible ordering with little waste. Mixing English and Italian in one description is slightly jarring for an agent parsing instruction text, but every sentence carries operative content.

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 definition covers the crucial rejection case and the full keyword object contract. It omits what the call returns (created keyword identifiers/status) and does not spell out bid currency or keyword_text constraints, minor gaps against otherwise solid coverage.

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?

The schema declares 'keywords' only as an untyped array with no item schema, so the description carries the entire payload contract: campaign_id, ad_group_id, keyword_text, match_type with the BROAD|PHRASE|EXACT enum, and bid. This is essential information found nowhere else and directly compensates for the opaque required parameter.

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 ('Create SP keywords') and immediately disambiguates from sibling tools by scope, since ads_create_sp_negative_keywords and ads_create_sp_product_targets exist. An agent can tell this creates positive keyword targets without opening the schema.

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 a concrete when-not condition: if the target ad group already has product targets, Amazon rejects with otherError, and the agent should instead create a keyword-dedicated ad group. It stops short of naming the sibling tool (ads_create_sp_ad_group) to perform that fallback, but the routing condition is explicit.

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