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

Annotations already establish read-only, idempotent, non-destructive behavior, so the bar is lower. The description adds useful context around owner-scoping and completion, but does not disclose output shape, pagination, or behavior for incomplete or invalid jobs.

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, front-loaded sentence states exactly what the tool does with no filler. Every word earns its place, and the key qualifiers 'owner-scoped', 'completed', and 'asynchronous' are included.

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 simple two-parameter, read-only fetch tool, the description covers the essential prerequisites and scope. It would be more complete if it mentioned the shape of returned findings or error behavior, but annotations and schema cover most operational concerns.

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 only 50%: job_id is well described in the schema, but format has no description. The tool description adds no parameter meaning, so it does not compensate for the undocumented format enum or explain the difference between 'full' and 'compact'.

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 uses a specific verb 'Fetch' and a precise resource: 'owner-scoped findings for a completed asynchronous batch scan.' This clearly distinguishes it from sibling tools like batch_scan_start and batch_scan_status, which begin or report scan progress rather than return findings.

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 states the key usage condition: the batch scan must be completed and asynchronous. This tells an agent when to call it, though it does not explicitly name alternatives or state that it should not be called before completion.

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