scan_buckets_start

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

With minimal annotations (openWorldHint:true, readOnlyHint:false), the description carries the burden of behavior disclosure. It effectively communicates the async nature, immediate return of scanId, the degradation behavior ('degrades to info when unprovisioned'), and the poll/retrieve workflow. This adds substantial non-obvious context beyond the annotations.

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?

Three sentences, each earning its place: purpose, constraint, and next steps. No fluff or repetition. Highly scannable and information-dense.

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 async start operation with two parameters and no output schema, the description covers the essential flow (start, poll, retrieve) and the degradation behavior. It misses details on parameter validation or error cases, but given the tool's moderate complexity, it is nearly complete. A small gap exists around the 'providers' parameter, but overall it is well covered.

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 0%, so the description must compensate. It clarifies that 'target' is a domain, which helps, but it says nothing about 'providers', its format, or possible values. With two parameters and no schema descriptions, this is a gap—leaving the agent underinformed about half the parameters.

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 clearly states 'Start an async cloud-bucket discovery scan for a target domain' with a specific verb ('start'), resource ('cloud-bucket discovery scan'), and target ('domain'). It is distinct from sibling tools like scan_buckets_status and scan_buckets_findings, which are explicitly referenced as follow-ups.

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 description provides clear context: it is async, returns a scanId immediately, and instructs the user to poll with scan_buckets_status and retrieve with scan_buckets_findings. The 'Operator-deploy only' caveat gives deployment context. However, it doesn't explicitly discuss when to use this tool versus alternatives or mention any exclusion scenarios.

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