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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds two non-obvious traits: records are redacted, and the cursor is single-use, which reinforces the idempotentHint=false behavior. It still omits what terminates the stream or what a record contains.

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?

A single dense sentence with no filler, and the scope qualifiers are front-loaded. It is tight but arguably too terse for a tool whose paging loop and termination conditions are not described anywhere.

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 burden of explaining the return shape, yet it says nothing about what a record contains or how the next cursor is obtained. Annotations cover the safety side and the schema covers inputs, so the definition is minimally viable but has a clear gap on results and paging termination.

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 description coverage is 100%, so all three parameters are documented in the schema itself, making 3 the baseline. The description's 'single-use cursor' phrasing corroborates the cursor parameter's documented behavior but adds no format, limit, or request-id detail beyond the schema.

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 verb ('Poll') and resource ('redacted request-scoped agent records'), with the qualifiers 'redacted' and 'request-scoped' narrowing scope meaningfully. It is distinguishable from siblings like get_request_status or get_result_bundle, though it never names an alternative to make the contrast explicit.

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?

There is no explicit when-to-use or when-not-to-use guidance and no sibling is named as an alternative. The word 'Poll' and the 'single-use cursor' hint at an iterative paging loop, but an agent must infer when this tool is preferred over the several request-related siblings.

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