compare_policies

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

No annotations are supplied, so the description carries the full burden. It says metrics are compared and cross-checked against a reference, but never states whether runs write files (work_dir), how expensive a multi-policy multi-seed sweep is, whether prior results are overwritten, or what the agent receives back.

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?

It is a single front-loaded sentence with no filler, which is good. However, the density of unexplained jargon (FIFO/SPT/EDD, 'standard metrics', 'reference cross-check') makes it terse at the expense of comprehension rather than efficiently informative.

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 tool with zero schema documentation, no annotations, and no output schema, the one-line description leaves too much unspecified. An agent would not know what values horizon or jitter expect, what 'standard metrics' are returned, or whether instance is an object or path.

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. The description only sheds light on two of them: 'policies' (FIFO/SPT/EDD or a subset) and 'seeds'. It says nothing about jitter, horizon, instance, or work_dir, which remain entirely opaque.

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 gives a specific verb ('Run') and names the concrete artifacts (FIFO/SPT/EDD policies, seeds, standard metrics, reference cross-check), so an agent can tell this is a policy-comparison/simulation tool. It stops short of differentiating itself from siblings like schedule_vs_reference or run_experiment, which remain ambiguous.

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 explicit statement of when to use this versus schedule_vs_reference, run_experiment, or reproduce_run, nor any prerequisites or exclusions. The phrase 'with reference cross-check' hints at validation intent but does not translate into actionable selection guidance.

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