Compose a multi-step workflow

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

With no annotations, the description reveals that the tool runs the entire workflow without human-in-the-loop and returns an attested trace, which is meaningful behavioral context. It does not cover failure behavior, blocking/async execution, permissions, or side effects, so transparency is partial.

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, front-loaded with the core concept, and each sentence earns its place by stating purpose, execution mode, step kinds, and return value. No redundant or filler text.

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?

The description covers high-level intent, step taxonomy, and return value, which is solid for a complex orchestration tool. However, it omits details about the meaning and usage of sub-fields (detail, system, sizeUnits), the format of the attested trace, and behavior on failure, leaving gaps given the nested schema and lack of output schema.

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 schema only describes the steps array but leaves the enum values opaque; the description adds semantic meaning by mapping each step kind ('observe a condition, request_proof, act, settle'). It does not explain detail, system, or sizeUnits, but the primary parameter is enriched.

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 uses the specific verb 'compose' and names the resource 'multi-step workflow', then details that it defines an ordered sequence autonomously executed by the surface. It distinguishes itself from sibling tools by being a meta-orchestration tool: it composes steps (observe, request_proof, act, settle) rather than performing a single 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?

It provides clear contextual guidance: use this when you want an agentic path with an ordered sequence that runs without human involvement. It does not explicitly name alternatives or state when not to use it, but the description makes the autonomous orchestration use case apparent.

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