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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the valuable disclosure that this is an asynchronous three-phase lifecycle (create, then poll, then download by token), which the annotations cannot convey. It still omits what an agent needs to run that lifecycle safely: how long polling takes, whether tokens expire, and any auth/connection prerequisites beyond connectionId.

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?

One tightly packed sentence that front-loads the contract reference and then delivers the three branching rules in order. Nothing is wasted.

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 14-parameter tool with a nested configuration object and no output schema, the description covers the most confusing part (which mode you are in) but leaves the heavy lifting of new-report composition to the schema. It is adequate to call the tool correctly, but an agent still has to infer interactions between configuration and the flat fields.

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 every parameter is already documented, including reportId and documentToken. The description usefully reinforces the mode-switching semantics of those two fields but adds no syntax, defaults, or guidance on how configuration replaces reportTypeId/adProduct/groupBy/columns. Baseline 3 is appropriate.

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 names the underlying operation (get_report) and enumerates the three modes it performs: create, poll, and download an Amazon Ads report. It is a specific verb+resource statement, but it never distinguishes this generic reporting tool from sibling tools like nexscope_amazon_ads_sp_insights_report_download or nexscope_amazon_ads_sp_insights_report_status.

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?

It gives concrete mode-selection rules: omit reportId to create, supply reportId to poll, supply documentToken to download. That is a real when-to-do-what mapping. It stops short of saying when to pick this tool over the sibling report-status/download tools, so it is clear context without exclusions.

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