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

Adds meaningful context beyond the annotations: the scan consumes the account's Scan allowance (a cost/quota constraint), it returns an ID immediately, and it is long-running so progress must be polled. However, despite destructiveHint=true, it never explains what is destroyed or overwritten by a run, leaving that side effect opaque.

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?

The confirmation requirement is front-loaded and each sentence carries distinct information (confirmation, setup review, quota, polling). The setup-review sentence is somewhat long, but it is not wasted verbiage.

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 an output schema present and only one parameter, the description covers everything an agent needs: consent requirement, quota implication, immediate ID return, and async polling guidance via a named sibling. Nothing material is missing.

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% and the single siteId parameter is fully documented in the schema (UUID format, source from list_sites_and_topics, subjectKind guidance). The description adds no parameter-level meaning, so the baseline of 3 is appropriate.

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 ('Starts a Scan for a brand site or topic using its latest saved setup and returns its ID immediately'), including the key behavioral fact that it is async and ID-returning. This distinguishes it cleanly from siblings like get_scan_status, list_scans, and get_scan_config.

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?

Explicit when-to-use and gating conditions: confirm with the user first, review objective/audiences/questions/entities/regions/models for new setups, and call only after confirmation. It also names the alternative for progress tracking (get_scan_status) and warns against busy-polling, leaving nothing to inference.

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