Reflect: Delete Previous Step

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the destructive nature is structurally available. The description adds useful constraints: the session must be active and only the last step is removed. It does not state whether deletion is reversible or what state the session is left in, but this is modest additional context on top of existing 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?

The core action is stated in one clear sentence, with no marketing or filler. The Toolset label is brief, though the Parameters section duplicates schema content without adding information. Overall this is efficient and front-loaded, with minor redundancy.

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 single-parameter destructive tool with annotations covering the safety profile, this is nearly sufficient. It identifies the required session ID, the 'active' precondition, and the exact scope ('last step'). It does not describe the response or failure modes, but given the low complexity that is a minor omission.

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?

The input schema already documents sessionId at 100% coverage, and the description's parameter block simply repeats that information verbatim. No additional meaning, such as where to find the session ID or required session state, is added. A baseline of 3 is appropriate because the schema fully covers the parameter.

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 ('Delete'), resource ('last step'), and context ('active Reflect recording session'). The one-sentence description unambiguously differentiates from sibling tools like reflect_add_prompt_step by targeting the most recently added step, so an agent knows exactly what this action performs.

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?

No guidance is provided on when to use this tool versus alternatives, such as how to remove an earlier step or whether a different Reflect tool should be used to modify the session. The description only implies the obvious use case (undo the last added step) and omits exclusions or caveats. This is a meaningful gap for a destructive action.

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