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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing the real cost model: one full-analysis allowance per product and across all products for the billing period, plus one page speed check. It also explains the async contract ('returns immediately') and the auth requirement (rescan scope), which is exactly the context annotations cannot carry.

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, front-loaded with the action, then cost, then poll instruction. Every clause is load-bearing — quota, auth scope, and polling target are all things the agent would otherwise get wrong.

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?

Although there is no output schema, the description covers the return behavior (immediate return, results land in get_insights), the cost side effect, and the auth prerequisite. For a one-parameter async mutation, nothing an agent needs in order to call it correctly 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?

The single productKey parameter is fully documented in the schema, including a pointer to list_products. The description reinforces the 'one product' scoping but adds no format or retrieval detail beyond the schema, so the baseline 3 for high coverage 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?

States a specific verb and resource ('Starts a fresh full analysis of one product') plus its execution mode ('in the background'), which cleanly separates it from read-only siblings like get_insights or get_scan_history. An agent knows exactly what this does without opening the schema.

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?

Gives clear when-to-use context (you want fresh numbers) and an explicit follow-up path: poll get_insights until scanPending is false. It also surfaces the precondition of a rescan-scoped key. It lacks an explicit 'when not to use' comparison against siblings such as run_site_report, which keeps it off a 5.

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