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

Annotations already declare the mutation/idempotency/open-world profile, so the bar is lower, and the description still adds real behavioral context: scans consume existing scan limits, depend on provider availability, and can trigger refunds (money/credits can come back on failure). It does not say whether the scan is synchronous or how failures surface.

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 short sentences, front-loaded with the action and its precondition, with no filler. The second sentence is dense to the point of being slightly cryptic about how limits/availability/refunds interact.

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?

An output schema exists so return values need no explanation, and annotations cover the safety profile, but for a credit-consuming mutation the description omits where credits come from, how much a scan costs, and how to track progress after starting.

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 carries the full burden, yet it only clarifies expectedCredits (must be pre-approved). brandId and targetId are completely unexplained in both schema and description, and idempotencyKey is only implicitly covered by the idempotentHint annotation.

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?

"Start a fresh scan" is a specific verb plus action, and "fresh" implies initiation rather than retrieving an existing scan, which helps separate it from get_intelligence_scan. It never says what is being scanned (an intelligence target) or contrasts itself with add_intelligence_target / list_intelligence_targets, so sibling differentiation is only partial.

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?

"Only after explicit approval of expectedCredits" is an explicit precondition for invoking the tool, which is unusually concrete guidance. It stops short of naming alternatives (e.g. use get_intelligence_scan to poll status) or stating when a scan should not be started.

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