Delimit Agent Handoff

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses concrete side effects: writes a handoff record via ai.agent_dispatch.handoff_task and updates the assignee on the task. This tells the agent exactly what state changes will occur and confirms the operation is a non-destructive but persistent mutation.

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 and well-structured, with short labeled sections for usage, exclusions, sibling contrast, and side effects. Every sentence carries distinct information, and the essential purpose is front-loaded in the first line.

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 three-parameter tool with a full input schema, annotations, and an output schema, this description covers when, when-not, how it differs from siblings, and its side effects. Nothing an agent needs to decide whether to call it is missing.

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 100%, so the schema already documents all three parameters clearly. The description adds no new parameter-level details, but it reinforces the context by explaining the handoff scenario and the role of the next model. Baseline 3 is appropriate given the full schema coverage.

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 opening sentence uses a specific verb and resource: 'Hand off an agent task to a different AI model.' It also names the exact sibling it is not (delimit_agent_complete) and clarifies that this transfers, rather than ends, the task. An agent can immediately distinguish it from close-out and dispatch tools without opening schemas.

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 explicitly states both when to use ('when an executor is blocked or when cross-model review is required') and when NOT to use ('to close out the task... or create a new one'), naming the alternative tools. This gives an agent clear, decision-ready routing guidance with no inference required.

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