執行一段 Agent 程式

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

Beyond the destructiveHint annotation, the description discloses sequential execution, per-step result reporting, and configurable stop-on-failure behavior. It does not detail the exact side effects or failure semantics, but adds meaningful behavioral context beyond the annotations.

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?

Two sentences with a clear front-loaded definition, followed by memorable use-case examples and the two most important behavioral switches. No filler or redundancy.

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 the highly detailed union schema and existing output schema, the description covers the tool's core role, examples, sequencing, per-step output, and failure policy. It omits prerequisites such as agent existence and parameter details, but those are less critical for selecting and invoking the tool.

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 description partially compensates for low schema coverage by clarifying that 'steps' are a chain of Agent actions and that stop-on-failure is configurable. It does not explain delayMs or the action object structures, leaving the rich item-level schema to carry most parameter meaning.

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 defines the tool as executing a sequence of Agent actions as a program, with concrete examples such as paving while walking, digging a tunnel, and tilling a field. It distinguishes the batch/program nature from single-action siblings, though it does not explicitly name an alternative.

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?

It provides clear context for when to use it: any multi-step, task-oriented Agent behavior, and calls it the main tool for making the Agent actually do things. It gives representative use cases, but does not explicitly say when to prefer single-action sibling tools.

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