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

With no annotations provided, the description carries full burden. It discloses important behaviors: coordinate fallback mechanism, per-step pass/fail result summary, and that validation failures are auto-skipped so replay never blocks. This is genuinely useful behavioral context beyond the schema.

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?

Three tightly-written sentences, each carrying distinct information: what it does, how it returns results, and the non-blocking behavior. Zero wasted words.

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 tool has no output schema but the description explains the return format (full result summary with per-step pass/fail status). It covers the core behavior, non-blocking failure handling, and coordination fallback. Could add explicit notes about device prereqs or interaction with flow_replay_status, but generally complete for a replay 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?

Schema description coverage is 100%, so the schema documents all 5 parameters well. The description adds context around validateElements (confirming failures auto-skip) and platform auto-detection, but mostly reinforces what the schema already states. Baseline 3 is appropriate.

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 replays a flow recording on a device, executing steps in order with element locators and coordinate fallback. It distinguishes reasonably from siblings like flow_replay_start/flow_replay_abort, though it doesn't explicitly contrast with flow_replay_start, making the differentiation somewhat implicit given flow_replay_start is in the sibling list.

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 indicates this is a single-invocation replay of an existing recording, contrasted implicitly with flow_replay_start/abort/status which appear step-oriented. It conveys the use case (replay a recording with auto-skipped validation) but doesn't explicitly name alternatives or state when not to use this tool.

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