finance_payroll

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

It discloses that the tool routes through a domain-agent dispatcher under JWT, tenant, and company scope, which is useful execution context. It does not add side-effect details beyond the annotations, but those already flag destructive/non-idempotent hints. No contradiction.

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 only five short lines and includes the essential parts: action call, routing context, and args. The opening line is somewhat redundant with the name, but the overall structure is efficient and easy to parse.

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 destructive-hinted payroll action, the description omits what the agent should put in the message/inputs, what payroll behaviors are triggered, or what outputs to expect. The output schema exists, but input construction and domain-specific consequences are not addressed.

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?

With zero schema descriptions, the description provides the only meaning for both parameters: 'message: Free-text objective' and 'inputs: Optional JSON string of structured inputs'. This clarifies the two parameters' roles, though it stops short of specifying the JSON structure or example values.

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 opens with 'Run the finance domain agent action `finance_payroll`,' which restates the tool name and only labels it as a finance-domain agent action. It never states what payroll operation is performed (e.g., process payroll, calculate pay, generate pay slips). The routing sentence is about mechanism, not purpose.

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 choose this tool over the many payroll-adjacent siblings ('company_payroll', 'xero_payroll_trueup', 'finance_xero_payroll_trueup'). The description simply states it runs under JWT/tenant/company scope, offering no use cases or exclusions.

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