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

Annotations already declare it a non-read-only, open-world, idempotent, non-destructive action. The description adds real value beyond that by disclosing that it consumes existing scan limits, depends on provider availability, and is subject to refunds - all credit-spend behavior an agent cannot infer from 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?

Two tight sentences with the action and its approval precondition front-loaded. Every clause contributes; no padding or repetition.

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?

The output schema relieves the description of explaining return values, and it covers the credit/refund angle well. But for a credit-spending mutation with four undocumented required parameters, three of which are never mentioned, it falls short of complete.

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 references expectedCredits indirectly via the approval precondition. brandId, targetId, and especially idempotencyKey format/role go entirely unexplained.

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 fresh scan') for an intelligence target, which distinguishes it from sibling reads like get_intelligence_scan and writes like add_intelligence_target. Clear enough to route without opening the schema, though it doesn't explicitly name a sibling.

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 one meaningful precondition - only run after explicit approval of expectedCredits - which is a genuine usage gate. However it names no alternatives and doesn't clarify the relationship to target creation or scan-retrieval tools, leaving selection guidance implied.

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