run_experiment

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

No annotations exist, so the description carries the full burden. It does disclose one important behavior — that results are persisted as reproducible records — but says nothing about where records land (presumably work_dir), whether the run is long-running or synchronous, whether simulation state is mutated, or what happens on failure or duplicate seeds.

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?

A single front-loaded sentence with zero filler and no repetition of the tool name. It is efficient and readable, though the brevity is partly a symptom of under-specification rather than disciplined editing.

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 six-parameter, two-required-parameter execution tool with no annotations, no output schema, and no parameter documentation, one sentence is far from sufficient. An agent cannot determine argument formats, expected runtime, or what a successful call returns.

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 six parameters, so the definition must compensate and does not. "Policy" and "seeds" are echoed from the parameter names, but instance, jitter, horizon, and work_dir — including their types and the fact that instance accepts an object or a string — receive no explanation at all.

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 pairs a specific verb ("run") with a specific resource ("one dispatch policy over one or more seeds") and adds the persistence/reproducibility outcome. An agent can tell this is a simulation-execution tool, although it does not name or distinguish itself from plausible siblings such as reproduce_run, simulation_run, or compare_policies.

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 when-to-use guidance, no when-not-to-use, and no mention of alternatives. With siblings like reproduce_run and simulation_run present, an agent gets no signal about which entry point to pick for a fresh run versus a reproduction.

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