sc_improve

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states 'enhance existing code' without mentioning whether the tool modifies files, requires permissions, or has side effects. The flags (--refactor, --clean) imply mutation, but the description does not disclose this behavior.

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?

The description is extremely short, but this is under-specification rather than conciseness. It contains no structured information, front-loaded key facts, or elaboration on the flags and parameters. The brevity fails to serve the agent's 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?

The tool has complex inputs (flags, persona, evidence object), no output schema, and no annotations. The description provides no context about the command's purpose, expected inputs, or behavioral outcomes. It is completely inadequate for an agent to invoke correctly.

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 100% since each parameter has a description. The tool description adds no parameter-level semantics, so the baseline score of 3 applies. The schema itself provides adequate parameter documentation, though the description does not reinforce or clarify it.

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 phrase 'Code improvement - Enhance existing code' indicates a broad purpose of improving code, but it lacks specificity about what kinds of improvements are offered or what resource is affected. It is somewhat more than a tautology because it rephrases 'improve' as 'enhance', but it does not clearly distinguish from sibling tools like sc_analyze or sc_cleanup.

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 description provides no guidance on when to use this tool versus alternative sibling tools. It does not mention any context, prerequisites, or exclusions, leaving the agent without any basis for tool selection.

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