finance_fraud_investigation

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

Annotations already claim destructiveHint=true, readOnlyHint=false, openWorldHint=true. The description adds no behavioral context such as side effects, auth needs, or what the action does internally. It only says 'run the finance domain agent action' and mentions routing—nothing about potential destruction or why the destructive hint exists. There is no contradiction, but the annotation burden is left completely unaddressed.

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 compact, with a clear top line followed by implementation context and an Args list. It earns its length, though the arg explanations are very thin. It doesn't ramble and puts the main action first.

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?

Given destructiveHint=true and openWorldHint=true, an agent needs far more warning context and guidance. The output schema exists, so return values are covered, but the description fails to explain what the fraud investigation does, what effects it may have, and when to invoke it. For a high-stakes finance action with dangerous annotations, this is incomplete.

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%; the description says 'message' is a free-text objective and 'inputs' is an optional JSON string of structured inputs. This is barely more than the schema's names/defaults. It doesn't say what should go in the message, what structured inputs are expected, or how to format the JSON string.

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 says 'Run the finance domain agent action finance_fraud_investigation' with a specific verb and resource, plus 'Finance domain agent action' clarifies the category. It doesn't get a 5 because it doesn't differentiate itself from sibling finance actions or state what the fraud investigation actually does—only that it is an agent action to run.

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?

The description states it routes through the domain-agent dispatcher under JWT/tenant/company scope, giving some context, but it never says when to use it versus alternatives, e.g., finance_anomaly_fraud_case_file or finance_anomaly_investigation. No exclusions or alternative conditions are provided.

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