hr_employee_offboarding_loop

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

The annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false, so the description doesn't need to restate them. The description adds context about routing ("under your JWT, tenant, and company scope") but does not disclose what an offboarding loop actually does: what gets terminated/disabled, whether it ends employment, whether it interacts with downstream systems, or what the output looks like. The word 'loop' suggests iterative processing, but the description never explains this behavior.

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: a one-line purpose, one line about routing, and a small arg list. It front-loads the primary action. Minor redundancy exists between "Run the hr domain agent action..." and "Routes through the platform's domain-agent dispatcher" but the text is generally efficient.

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?

There is a large sibling list of related HR tools (hr_offboard, hr_onboard, hr_employee_hire_onboarding_loop, hr_live_cases, etc.) and no output schema explanation beyond the tool's own output_schema presence. The description doesn't explain what an offboarding loop produces, what the flow is, when it would terminate, or how it relates to `hr_offboard`. For a destructive, non-idempotent action, this is a significant completeness gap.

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 input schema has 2 parameters with 0% schema description coverage, so the description carries some burden. It partially compensates by defining `message` as "Free-text objective for the action" and `inputs` as "Optional JSON string of structured inputs for the action." These definitions are adequate for a generic domain-agent dispatcher pattern, but they lack any HR-specific guidance about what should go in `message` or valid keys in `inputs`.

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 states that the tool runs the HR domain agent action `employee_offboarding_loop` and routes through the platform's domain-agent dispatcher. This identifies what the tool does (runs an offboarding loop in the HR domain) and differentiates it from direct HR actions like `hr_offboard` or `hr_live_cases`. However, it does not explain what the offboarding loop itself accomplishes (e.g., steps through employee offboarding tasks) beyond the name, and the description reads more like an internal execution detail than a user-facing 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?

The description indicates this tool is for the HR domain agent action `employee_offboarding_loop` — an implicit hint that it should be used when running the offboarding loop through the agent dispatcher rather than calling a direct HR tool. However, it does not explicitly state when to prefer this over siblings like `hr_offboard` or `hr_employee_hire_onboarding_loop`, nor does it name exclusions or alternatives.

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