rr_record

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

No annotations provided, so description carries full burden. Discloses that crashes are recorded normally, stdin is unavailable, and timeout behavior. Does not mention potential side effects or system prerequisites, but covers key behavioral traits.

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?

Description is well-structured with a brief overview, then bullet points for parameters. Every sentence adds value, no redundancy. Front-loaded with purpose and workflow context.

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 no output schema, description explains the return value (trace_dir). Covers parameter details and important behavioral notes. Could mention that it returns a string path, but overall adequate for the tool's complexity.

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?

Input schema has 0% description coverage, so the description compensates fully: explains binary, args, cwd (with default), and timeout (with default). Each parameter gets meaningful explanation beyond schema types.

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 action ('Record a full program execution'), the tool (rr for time-travel debugging), and its place in the workflow ('Step 1'). It distinguishes itself from siblings like 'start_replay_session' and 'run' by noting it captures a deterministic trace and returns trace_dir.

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 it's the first step and that trace_dir is passed to start_replay_session. Includes important context: crashes and non-zero exit codes are normal, stdin unavailable. Does not explicitly say when not to use, but the workflow context is clear.

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