Re-dive an Existing Niche

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

Annotations only declare destructiveHint=true and readOnlyHint=false. The description adds substantial behavioral context: token spend per ASIN batch, irreversibility, non-idempotency (each call spends tokens and starts a separate re-dive), asynchronous execution returning `diveId` and `estimatedCompletionDate`, the expected polling flow, and that the `nicheId` persists so rank radars/reports follow refreshed data. This far exceeds the annotation baseline and contradicts nothing.

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: purpose and sibling distinction first, then critical cost/destructive warnings, then modes, then async behavior and persistence. Every sentence earns its place. It loses a point only for being a single wall of text with many embedded qualifiers — minor segmentation would aid scanning — but it is far from bloated.

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 complex tool with 7 parameters, destructive side effects, two modes, mode-dependent parameters, and no output schema, the description is remarkably complete. It explains return values (`diveId`, `estimatedCompletionDate`), the full async lifecycle (poll `get_dive_status` until `success`), cost behavior, and the persistence guarantee, while correctly referencing sibling tools (`get_dive_status`, `create_niche_dive`). Nothing an agent needs to invoke it correctly is missing.

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 baseline is 3, and the schema already documents each parameter well. The description adds value beyond the schema by connecting parameters to modes (`same_competitors` needs no other argument; `discover` is sized by `numberOfCompetitors` and steerable by `heroAsin`/`lockedAsins`/`excludedAsins`) and by adding the user-approval requirement for `confirm`, which the schema does not convey.

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 ('refresh'/'re-dive'), a specific resource ('an existing niche'), and immediately distinguishes itself from the sibling `create_niche_dive`. An agent can tell exactly what this tool does and how it differs from the nearest alternative without opening the 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 names `create_niche_dive` as the alternative and tells the agent to use this tool instead of creating a new niche. It also gives mode-selection guidance (`same_competitors` for refreshing stale data, `discover` when the niche has changed) and retry guidance (poll `get_dive_status` on error/timeout rather than re-calling). Nothing is left to inference.

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