Create a Rank Radar

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

The description goes well beyond the annotations. It discloses that the operation spends Search Term tokens, that cost scales with numberOfKeywords, that it cannot be undone, that it is not safe to retry, that the first call is a preview that may return warnings, that warnings must be shown verbatim, and that a warning never blocks creation. The annotations already declare destructiveHint=true, but the description adds critical context about token cost, retry safety, and the warning-handling protocol. No contradiction with annotations.

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 dense but well-organized: it front-loads the purpose, then the critical warning, then the retry guidance, then the warning-handling protocol, then the return value and prerequisites. Every sentence earns its place, though the length is substantial. It could be slightly tightened, but the density is justified given the high-stakes nature of the operation.

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 destructiveHint=true, no output schema, and 4 parameters, the description is remarkably complete. It covers prerequisites (nicheId from list_niches), cost behavior, retry safety, warning handling, return value (rankRadarId), and follow-up tool (get_rank_radar_data). An agent has everything needed to invoke this correctly and safely.

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%, so the schema already documents all four parameters. The description adds meaningful context beyond the schema: it explains the cost implication of numberOfKeywords, the confirmation requirement for confirm, the source of nicheId (list_niches), and the minimum for numberOfKeywords. It doesn't add syntax details for asin, but the schema already covers that. This is a strong complement to the schema, though not a full 5 because the schema already does most of the work.

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 states a specific verb ('start tracking'), a specific resource ('organic and sponsored keyword rankings for an ASIN within a niche'), and clearly distinguishes this from sibling tools like list_rank_radars, get_rank_radar_data, and delete_rank_radar. The title and description align, and the scope is 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?

The description explicitly says when to use this tool (to start tracking rankings), and provides clear exclusions: 'Not safe to retry: each call spends tokens again and creates a separate Rank Radar — if a call errors or times out, check list_rank_radars instead of re-calling.' It also names the prerequisite source for nicheId (list_niches) and the follow-up tool (get_rank_radar_data). This is explicit when/when-not guidance.

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