Agent Work

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

Annotations already declare that the tool is not read-only, is open-world, is non-idempotent, and is non-destructive. The description adds value by naming the state-changing operations it can perform, such as checkout, complete, heartbeat, and review submission, but it does not disclose permissions required, side effects, failure modes, or what completion/rejection actually changes.

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 two sentences and front-loads the operation inventory before the invocation instruction. It is efficient and free of filler, though the dense operation list is not structured by action sequence or workflow.

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?

This is a complex mega-tool with 12 actions, 31 parameters, a discriminated-union schema, and no output schema. The description provides only a high-level inventory and one invocation instruction; it omits per-action requirements, when each action should be used, handoff/review sequencing, and what each operation returns.

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% across 31 parameters, so the description must compensate and largely fails to do so. It only clarifies that `action` selects the operation; it gives no meaning for required per-action fields such as `agentId`, `taskId`, `reviewerId`, `summary`, `feedback`, `strategy`, or `status`.

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 clearly states that this is an agent work lifecycle tool and enumerates the supported operations, including registration, task checkout/release/complete, heartbeat, review, validation, and handoff context. It does not differentiate this tool from the sibling `agent_manage` tool, which likely overlaps with the 'register agents' operation.

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 only guidance is 'Use the `action` field to select the operation,' which explains invocation mechanics but not when to use this tool versus siblings like `agent_manage`, `manage_issues`, or `manage_prs`. There is no per-action guidance on prerequisites, sequencing, or exclusions.

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