reverse-step

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

Discloses that it blocks until stopped and enters called functions when going backwards. With no annotations, this is sufficient behavioral context for a debugging tool, though it could mention constraints like only moving within recorded execution.

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?

Concise and well-structured: 5 sentences cover rr-only context, behavior, requirements, sibling differentiation, and parameter details. No 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?

Given the existence of an output schema, the description adequately covers what the tool does and its key parameters. Missing error conditions or end-of-recording behavior, but overall sufficient for a step 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?

Description adds meaning for 'count' and 'instruction' parameters, but fails to describe the required 'session_id', which is essential. With 0% schema description coverage, the burden is higher, and the gap reduces the score.

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 indicates the tool steps backwards into the previous source line or machine instruction, specifying the verb 'step backwards' and the resource. It distinguishes itself from sibling 'reverse-next' by noting it enters called functions.

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?

Explicitly states when to use this tool vs. reverse-next, and that it requires an rr replay session created with start_replay_session. Provides clear context and alternatives.

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