Create a Rank Radar

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

Goes well beyond the annotations: states the operation cannot be undone, costs Search Term tokens scaling with numberOfKeywords, requires confirm:true after user approval, and creates a separate Rank Radar on each call. This materially changes how an agent should invoke and handle failures.

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?

Every sentence adds necessary operational guidance for a destructive, cost-incurring action. The purpose is front-loaded, followed by the key warning, retry guidance, output info, and prerequisites. No filler.

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 4-parameter destructive tool with no output schema, the description covers invocation, required inputs, cost behavior, user confirmation, failure recovery, output identifier, and follow-up reading. Nothing critical is missing for correct selection and invocation.

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?

Although the schema already documents all parameters well, the description adds crucial behavioral semantics: cost scaling with numberOfKeywords, the confirmation requirement for confirm, and that nicheId comes from list_niches. It also notes the return value and how to read the data later.

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, actionable purpose: start tracking organic and sponsored keyword rankings for an ASIN within a niche. This clearly differentiates it from siblings like list_rank_radars, get_rank_radar_data, and create_niche_dive.

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 tells the agent when to use the tool, warns that it spends tokens and is destructive, and instructs that on error/timeout it should check list_rank_radars rather than retry. Also notes the prerequisite of obtaining nicheId from list_niches.

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