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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds non-obvious behavior beyond them: the default PAUSED state so the group can be populated before delivery, and the Amazon otherError rejection when mixing keyword and product targets. These are the kinds of domain constraints an agent cannot infer from structured fields.

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?

Purpose is front-loaded, then the critical mutual-exclusion constraint, with no padding. The only friction is the abrupt switch into Italian for the most important paragraph, which costs a bit of readability for a general agent.

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 create tool with no output schema, the description covers the essential creation semantics and the key failure mode. It stops short of saying what the call returns (e.g., the new ad group ID needed for follow-up populate calls), which would fully close the loop.

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 67%, and account_id and confirm_id already carry descriptions in the schema. The description mentions no field-level semantics (state, default_bid, campaign_id, profile_id) and does not even reference the two-step confirm_id flow, so it adds little beyond the schema. Baseline 3 for moderate coverage is appropriate.

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+resource+scope: 'Create a SP ad group in an existing campaign.' An agent can immediately distinguish this from ads_create_sp_campaign or ads_update_sp_ad_group without opening any 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?

Explicitly explains when to create one vs two ad groups, names the alternatives (ads_create_sp_keywords, ads_create_sp_product_targets) and the condition that selects each, and clarifies that negative keywords/targets are exempt from the rule. This is exactly the when/when-not/alternatives guidance the dimension wants.

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