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

Annotations already declare write/destructive/open-world, but the description adds genuinely new behavioral context: the run can take minutes, it is queued and returns a run id immediately rather than blocking, and the agent must poll get-phone-run-tool until success or failure. That async contract is the key fact an agent needs and is not derivable from 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?

Front-loads what the tool does, then the precondition, then the two input modes as a compact bulleted either/or. Slightly dense but every sentence carries an operational constraint; the alternative-tool note is placed exactly where the ambiguity arises.

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 destructive, open-world, no-output-schema tool it covers the full loop: prerequisite state check, one-of input modes, async queue-and-poll return semantics, and the sibling to use for natural-language tasks. An agent has everything needed to call it and handle the result.

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 coverage is already 100%, so baseline is 3, but the description adds real meaning: slot must be the UUID not the display name, workflow must be a name from list-macros-tool, params fill {{placeholders}} and must be scalars, and steps are run as-is with each needing an action.

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?

States a specific verb+resource+scope: 'Replay a recorded macro (or a raw step list) on one farm phone: exact taps, swipes and typing, with no AI deciding anything.' It explicitly differentiates itself from the sibling run-phone-agent-tool, so an agent can route without opening either schema.

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?

Gives explicit when-to-use (recorded macro or raw step list), when-not (tasks described in words → run-phone-agent-tool), a precondition (phone must show video_live: true in list-phones-tool), and the mutual-exclusion rule for workflow vs steps. Nothing is left to inference.

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