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

With no annotations, the description carries the behavioral burden. It meaningfully discloses that runs are queued, return immediately, and may take minutes, plus instructs the agent to poll the phone or account for the outcome. It does not cover failure modes or response shape.

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 well-structured, front-loads the key constraint, and uses a compact bullet list for the mutually exclusive options. It earns its length, though it somewhat duplicates schema 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?

For a 4-parameter async tool with no output schema or annotations, the description covers the essential invocation constraints, the two modes, and what to do after calling. It does not state what the immediate return value is, which is a minor 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?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds some context (registry resolution, scalar params, steps needing an 'action'), but this is largely redundant with the schema.

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 the tool runs a step list on a farm phone and distinguishes the two input modes (workflow vs steps). It does not explicitly differentiate from sibling tools like run-phone-agent-tool, so it misses the top of the scale.

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 gives clear preconditions ('slot must be cast/live') and an explicit exclusivity rule ('Give exactly one of workflow or steps'). However, it does not say when to choose this tool over alternatives or when not to use it.

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