replay_run

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

With no annotations, the description carries the full burden. It does disclose the important behavior that commands are actually re-executed and that success is defined as matching exit codes plus identical output hashes, which is genuinely useful. However, it omits side-effect/permission warnings (re-executing arbitrary recorded commands can mutate state) and any sandboxing or auth context, which matters most for a re-execution tool.

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?

Three short sentences, front-loaded with the action and then the success criterion; no filler. The 'True reproducibility = ...' line earns its place by pinning down the pass condition.

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?

An output schema exists, so per-step return details need not be restated. Still, for a tool that re-executes recorded commands, the description should cover the run_file prerequisite, cwd role, and side-effect expectations; those gaps leave an agent under-informed about a potentially stateful operation.

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 0% across 2 parameters, so the description must compensate and does not: run_file is never identified as a path to a recorded run, and cwd (with its default) is not mentioned at all. Nothing is added beyond the bare schema property names.

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 (re-execute) plus resource (every recorded command in a run) and adds the comparison mechanism (output hashes). It is clear what the tool does, but it does not differentiate itself from the sibling check_run or provenance_report, which plausibly overlap in the reproducibility-check space.

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?

There is no statement of when to prefer replay_run over check_run, provenance_report, or the record_step/list_stored_runs pair. Usage is only implied by the verb; no prerequisites (e.g. that a run must first have been recorded) or exclusions are given.

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