suggest_ppc_keywords

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

With no annotations, the description carries full responsibility for revealing behavior. It reveals several non-obvious traits: terms are harvested from competitor titles, bids are derived from unit profit, and a break-even CPC is returned as a hard ceiling. It does not mention the full calculation factors or what happens when optional financial fields are omitted, but the core behavioral contract is well covered.

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 compact and information-dense, packed with exactly what matters: match type, bid range, priority, campaign, competitor sourcing, negative keywords, and break-even stake. There is no filler, repetition, or vague phrasing, and the most essential output is front-loaded.

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?

The description gives a strong overview and acknowledges important constraints, and an output schema exists to define return structure. However, with eight parameters and 0% schema coverage, leaving the financial-injection model implicit creates a real gap. An agent can likely make a correct basic call, but edge cases around ACoS, cost, conversion, and profitability inputs are not sufficiently contextualized.

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 provides no parameter-level descriptions, so the description must compensate. It references profit-related input via 'derived from your unit profit' and competitor terms via 'harvests terms from competitor titles', but it does not explain category, target_acos, product_cost, conversion_rate, or how selling_price is used. Several important optional parameters are left undefined despite being central to bid calculation.

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?

The description identifies a highly specific outcome: Sponsored Products keyword suggestions with match type, bid/bid range, priority, campaign placement, negative keywords, and break-even CPC. This clearly separates it from sibling tools like calculate_ppc_bids and plan_ppc_campaign. It also scopes the tool to Amazon Ads, making the resource unambiguous.

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?

It clearly describes the context of use—generating a full PPC keyword plan for a specific product, including competitor harvesting and campaign placement. It does not explicitly route the agent away from alternative tools like calculate_ppc_bids or plan_ppc_campaign, so it stops short of a 5. But the tool's purpose is clear enough that an agent can decide when to invoke it.

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