Create a Niche Dive

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

Annotations declare destructiveHint=true, and the description substantially enriches this: token spend that scales with numberOfCompetitors, 'cannot be undone,' non-idempotency ('each call spends tokens again and starts a separate dive'), and the async contract (immediate diveId + estimatedCompletionDate, poll until success carries nicheId). These behavioral details go far beyond what annotations alone convey and are exactly what an agent needs before invoking a paid, irreversible operation.

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?

Roughly 130 words for a tool that is destructive, paid, non-idempotent, and asynchronous — every sentence has a distinct job, and the purpose is front-loaded. It is efficient but slightly dense; the retry sentence bundles token cost, idempotency, and error-recovery alternatives into one long clause. Cleaner separation of the warnings would earn a 5.

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?

With no output schema, the description carries the full burden of explaining the return contract, and it does: immediate diveId + estimatedCompletionDate, polling via get_dive_status, and the nicheId delivered on success for use with list_niches, get_niche_keywords, etc. Combined with cost, confirmation, and retry warnings, nothing an agent needs to call this tool safely 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. The description adds genuine cross-parameter semantics on top: numberOfCompetitors drives cost, and confirm must be true only after the user approves that cost. It also reinforces the required trio (marketplace, asin, numberOfCompetitors). It wisely does not duplicate the marketplace enum gotchas, which the schema already documents thoroughly.

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 opening sentence states a specific verb and resource: 'start new niche research from a seed ASIN.' The 'new' qualifier implicitly separates it from the re-dive sibling (redive_niche), and the polling workflow content distinguishes it from the read-only status tools. An agent can tell exactly what this tool creates and from what input.

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 gives explicit when-to-use ('start new niche research') and names concrete alternatives with conditions: 'if a call errors or times out, poll get_dive_status (or check list_niches) instead of re-calling.' It also specifies the confirmation prerequisite — set confirm: true only after user cost approval. This is precisely the guidance needed to prevent the tool's dominant failure mode (duplicate paid dives).

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