split_rom

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

With no annotations, the description carries the full behavioral burden, and it only partially delivers: it discloses the dry-run default and that an external CLI is invoked. It does not say whether outputDir is created or overwritten, whether the operation is reversible, what the RETRACE_ALLOW_WRITE environment gate requires, or what failures look like. Those omissions matter for a tool that can mutate the filesystem.

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?

Two short sentences, front-loaded with the core action and followed by the safety-relevant default. Nothing is wasted or redundant.

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 4-parameter, partially write-capable tool with no annotations, no output schema, and 75% of parameters undocumented, the description is too thin. An agent cannot tell from it what the returned tree contains or what the preconditions for a successful run are.

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 only 25%, and only the apply parameter is documented (in the schema, not the description). The description adds no meaning for romPath, configPath, or outputDir — for example whether configPath must be a splat YAML, or whether outputDir must be empty. With low coverage, the description should compensate but does not.

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 names a specific action and resource: running the installed splat CLI against a versioned config to produce a generated tree. That distinguishes it reasonably well from nearby siblings such as decomp_config_apply_changes and build_run, though it never states the relationship to those tools explicitly.

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?

"Dry-run is the default" implies a preview-first workflow and hints that a write run must be opted into, which is useful implied guidance. But there is no explicit statement of when to choose this tool over decomp_config_validate, decomp_config_apply_changes, or build_run, and no prerequisites are given in the description.

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