batch_scan_start

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

Annotations already declare idempotentHint=true, so the description earns credit for going further by spelling out the exact replay conditions — same principal, normalized inputs, and scoring versions return the same job — which is real operational context an agent cannot get from the boolean hint. What is missing is job lifecycle information: TTL, whether results expire, and how to retrieve them.

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, zero filler, with the core action and its return value front-loaded before the idempotency nuance. Nothing repeats the schema or annotations verbatim.

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 an asynchronous batch-start tool with no output schema, the description should close the loop by pointing at the status/findings siblings and describing job lifetime. It covers initiation and idempotency well but leaves the agent without an explicit retrieval path, which is the most consequential remaining gap.

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 the schema already documents all four parameters including idempotency_key and force_refresh, which puts the baseline at 3. The description reinforces the 1–10 domain bound and adds genuine replay semantics for the idempotency key, but leaves format and force_refresh entirely to the schema, so it does not rise above baseline decisively.

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 and resource ('Start a durable asynchronous scan of 1–10 domains') plus the immediate result ('Returns a stable job ID'), so an agent knows exactly what the tool initiates. It stops short of naming the companion poller (batch_scan_status) or distinguishing itself from the non-start sibling batch_scan, so differentiation is inferred rather than stated.

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 words 'durable asynchronous' and 'job ID' imply the follow-up pattern (start, then poll a status tool), but no explicit when-to-use, when-not-to-use, or alternative is named. An agent in a toolset containing batch_scan, batch_scan_status, and batch_scan_findings must guess the intended workflow.

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