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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: remaining steps are renumbered and the returned step list reflects new indices, and deleting the appLaunch step (index 1) is rejected. It also implies the operation is destructive (removes a step). This is strong but does not explicitly state irreversibility or any permission requirements, which are not critical here.

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 three sentences, front-loaded with the primary action, then use cases, then side effects and constraints. Every sentence earns its place with no fluff or repetition.

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?

Even without an output schema, the description explains what the agent receives (the returned step list with new indices) and covers the error case (appLaunch deletion rejected). It provides enough context for correct invocation, including the source of the stepIndex.

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%, so the baseline is 3. The description adds value by directing the agent to use stepIndex from a flow_recording_action or flow_recording_get response, and clarifies the 1-based renumbering behavior. This goes beyond the schema's terse parameter descriptions.

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 action ('Delete one step from an in-progress recording') with a clear resource (a step within a recording) and context (before save). It distinguishes from siblings like flow_recording_replace_step and flow_recording_cancel by specifying its unique role of removing a mis-recorded step without restarting the flow.

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 when-to-use guidance: applies to in-progress recordings before save, and provides use cases (mis-recorded assert, stray tap). It also tells the agent where to obtain the stepIndex (from flow_recording_action or flow_recording_get). However, it does not explicitly contrast with flow_recording_replace_step, leaving a minor gap in alternative selection.

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