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

The description directly contradicts the annotations: annotations set idempotentHint=false, yet the description states that replaying the same idempotency key returns the same job, which is an idempotency guarantee. The durable-async and stable-job-ID details are useful but are undermined by this contradiction.

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?

Two sentences with no filler. The first sentence front-loads the action and scope, and the second adds the crucial replay behavior. Nothing is repeated from the schema.

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 4-parameter async starter with no output schema, the description states the key return value (stable job ID) and the durable nature of the scan. It does not explicitly point to status/findings siblings or explain when force_refresh should be used, but the schema covers parameter meanings and the overall workflow is mostly inferable.

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 the schema already documents all four parameters. The description adds useful context around idempotency_key behavior but does not need to repeat parameter syntax; baseline 3 applies.

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 opens with 'Start a durable asynchronous scan of 1–10 domains', giving a specific verb, resource, and scope. The 'durable asynchronous' phrasing and 'Returns a stable job ID' clearly distinguish this from phase-based siblings like batch_scan_status and batch_scan_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?

The usage context is implied by the verb 'Start' and the job-ID semantics, but no explicit when-to-use or alternative tools are named. An agent must infer that this is the initiation step for a batch scan and that status/findings tools are the follow-up.

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