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

Annotations already declare readOnlyHint=false and openWorldHint=true, and the description adds no behavioral context at all: no cost/credit implications, rate limits, pagination behavior, or country/language requirements. There is also visible tension between a clearly retrieval-style "discovery/mining" tool and readOnlyHint=false, which the description neither explains nor reconciles.

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 text is dominated by a repetitive trigger list with duplicated entries ("FBA profit screening" / "FBA profitability screening", "keyword-based product selection" twice). The one genuinely useful sentence — keyword-driven selection by conversion, clicks, and profitability — is buried at the end rather than 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?

For a 35-parameter filtering tool with no output schema, the description should convey what a result row contains and how filters/sorting interact. Instead it stops at audience-matching phrases, leaving the agent to infer the returned metric set (clicks, conversion, FBA fee, margin) and paging semantics entirely from the schema.

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 input schema documents all 35 parameters at 100% coverage, including sortField enum options, min/max range pairs, country codes, and 0-1 rate scaling, so the baseline is 3. The description contributes nothing beyond that — it mentions conversion rate, click volume, and profitability as ranking dimensions but adds no filter syntax or default behavior of its own.

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 first clause names a resource and activity ("Amazon product discovery and potential bestseller mining via Nexscope data"), so the general purpose is inferable, and the closing sentence ties it to keyword-driven selection ranked by conversion rate, click volume, and profitability. However, the rest is a trigger-phrase list rather than a description, and it never distinguishes this tool from many close siblings such as nexscope_amazon_opportunity_search_by_metrics, nexscope_amazon_market_product_search, or nexscope_data_jm_product_discovery.

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 lists situations that should "trigger" the skill (product mining, bestsellers, FBA profit screening) but gives no when-not-to-use guidance and never names an alternative tool for overlapping tasks. An agent facing the large family of Amazon discovery/research siblings gets no routing criteria beyond keyword matching on user phrasing.

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