perf_sched_replay

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

No annotations are provided, so the description carries the transparency burden. It explicitly says the tool 'simulate[s] the original scheduling' and 'reports statistics,' making its non-destructive simulation nature clear. It also notes the required prior recording step. It could add more detail about potential side effects, but the simulation wording effectively conveys the behavior.

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 short but contains redundancy: the first sentence ('Replay recorded scheduler events to simulate the original scheduling') and the second ('Replays the workload's scheduling decisions...') say essentially the same thing. The 'Output' and 'Requires' lines are useful and well-structured, but the duplicate opening could be condensed.

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 presence of a full input schema and an output schema, the description provides sufficient context: it states the output (throughput, latency) and the prerequisite (perf sched record). This is adequate for a specialized replay tool, though it could optionally describe how statistics are computed or what 'simulate' means operationally.

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 description coverage is 100%, and the schema already documents all 8 parameters with concise explanations. The description does not add extra meaning to the parameters (e.g., how 'cpu' filtering interacts with replay), so the baseline score of 3 is appropriate.

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 uses a specific verb+resource ('Replay recorded scheduler events') and clearly states what the tool does: simulates original scheduling and reports statistics. It distinguishes itself from sibling tools like perf_sched_map and perf_sched_latency by focusing on replay behavior and statistical output.

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 clearly states 'Requires: perf sched record,' giving an explicit prerequisite and implying when to use the tool (after recording events). However, it does not mention alternatives or explicitly when not to use this tool compared to other sched subcommands.

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