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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'read-only' and 'No target is created or changed' largely restate structured data. The description does add one genuine behavioral signal — that it reuses the same research and optional curation services as campaign setup, implying cost, latency and AI-driven variability. It leaves the notable idempotentHint=false unexplained: nothing warns that repeated calls may return different suggestions.

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?

Three short sentences, front-loaded with the purpose, then the safety caveat, then the prerequisite. No filler, though the middle 'No target is created or changed' sentence is partly redundant with the leading 'read-only'.

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?

A 12-parameter tool with no output schema needs the description to say more about what comes back (suggestion objects, match types, volumes, whether curation is applied per-call) and about the optional curation/AI inputs. The description covers motivation and safety but leaves the agent guessing on the majority of the input surface and on the shape of 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 only 33% and the description compensates for almost none of it, ignoring count, ai_review, match_types, target_kinds, source_brand, source_price, source_title and source_category. The one parameter it does explain (profile_id from list_profiles) is already documented in the schema. With two unenumerated array parameters (match_types, target_kinds) left completely undefined, an agent cannot tell what valid values or defaults look like.

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 ('Generate'), specific resources ('keyword and product/ASIN target suggestions') and names the input that drives them ('source ASIN'). The phrase 'No target is created or changed' separates it cleanly from the mutating prepare_keyword_create_v1 / prepare_product_target_create_v1 siblings without requiring the agent to open either 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?

Provides clear context for use: research/curation ahead of campaign setup, with an explicit non-mutation guarantee, plus a hard dependency ('profile_id must come from list_profiles'). It stops short of explicitly naming when to prefer a sibling (e.g. 'use prepare_product_target_create_v1 to actually create the target'), so routing is implied rather than spelled out.

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