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

With no annotations provided, the description fully carries the behavioral disclosure burden, and it excels. It discloses the terminal-state no-op behavior, the watchdog bounds, and even the subtle detail that flow_replay_status may take a few seconds to reflect 'aborted' because an in-flight device call cannot be interrupted mid-flight. This is exemplary transparency beyond what any annotation would convey.

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 appropriately sized for the behavioral complexity it needs to convey—roughly three sentences that each earn their place. It front-loads the core purpose ('Abort an in-flight replay... Forces the replay to a terminal aborted state') and appends important caveats (no-op behavior, delay in status reflection). It's somewhat dense but not wasteful.

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 involves nuanced semantics (in-flight cancellation, terminal states, watchdogs, delayed status reflection) that the description captures comprehensively. Despite having only one simple parameter, no output schema, and no annotations, the description leaves no important behavior unexplained. It even anticipates a potential user confusion (why status might lag) and addresses it directly.

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 100% and the single parameter (replayId) is well documented in the schema. The description adds value by specifying the parameter's provenance (returned by flow_replay_start or flow_recording_replay), reinforcing where to obtain it. Since the schema already documents the parameter clearly and there is only one parameter, the description's added semantic context is solid without being redundant.

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 states a specific verb+resource combination ('Abort an in-flight replay') and explicitly names the initiating tools (flow_replay_start, flow_recording_replay), which clearly distinguishes it from sibling tools like flow_replay_start and flow_replay_status. It also specifies the outcome (terminal 'aborted' state), leaving no ambiguity about what the tool does.

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 provides explicit when-to-use guidance: use when a replay stops making progress (e.g., after a device/control-connection error) rather than polling flow_replay_status indefinitely. It also explains alternative behaviors—a watchdog (90s per-step, 15min overall) auto-terminates, and this tool is for cancelling sooner or cancelling an unneeded replay. It also conditions a no-op for already-terminal replays, which is valuable.

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