palace_run

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

With no annotations, the description carries the full burden and does disclose real behavior: it blocks until done, it self-refuses under resource pressure, force overrides that guard, and it writes palace.log, time.log, and run_record.json. It still omits timeout behavior, failure/rollback semantics, and side effects on the case directory.

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 with zero filler: the action and blocking nature come first, then the safety guard, then the artifacts produced. Every clause adds information an agent needs.

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?

There is no output schema and no annotations, so the description is the only behavioral source, yet it covers only 3 of 10 parameters and gives no return-value detail beyond the names of log files. For a long-running, resource-gated job launcher this leaves significant gaps.

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 10 parameters, so the description must compensate and largely does not. It only gives meaning to case_dir, config, and force, leaving cmd, image, ranks, distro, backend, dry_run, and timeout_s completely unexplained.

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 and resource ('Run Palace on case_dir/config') plus the scoping constraint that it blocks until completion. This clearly separates it from read-oriented siblings like palace_status, palace_results, and palace_estimate_cost.

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 refusal conditions (oversubscribed job, short RAM) and the 'unless force' escape hatch imply when the tool will and won't execute, which is useful routing context. However, it never says when to prefer this over siblings (e.g., palace_estimate_cost or palace_check first), nor when to use the undocumented dry_run flag.

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