run_fraud_agent_cases

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says 'Run' without explaining whether this starts long-running jobs, writes data, returns results, or has side effects on the evidence packs. For an action-oriented tool, this is a significant transparency gap.

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 description is a single, front-loaded sentence. It uses no filler and every word contributes to describing what the tool does.

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 a side-effecting 'run' tool with no annotations, no output schema, and minimal parameter explanation, the definition is incomplete. It communicates the high-level intent but lacks context about effects, output/return behavior, and how to discover the supported fraud specialist IDs.

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 schema provides no description for agent_id, and schema coverage is 0%, so the description must compensate. The phrase 'one of the 10 fraud specialists' gives some semantic meaning to agent_id, but it does not explain how to obtain valid IDs or connect this to list_fraud_agents.

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 uses a specific verb ('Run') and resource ('evidence pack'), and the plural 'every' distinguishes it from the sibling run_fraud_case, which implies a single case. The scope is clear: all evidence packs owned by one of the 10 fraud specialists. It lacks an explicit contrast with sibling tools, but the distinction is recoverable.

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?

There is no guidance on when to use this tool versus run_fraud_case, list_fraud_cases, or list_fraud_agents. The description implies a batch operation for a specialist, but it does not state prerequisites, exclusions, or how to choose among alternatives.

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