Audit a Claude Code setup

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

No annotations are present, so the description carries the full burden. It discloses the main behavior (scoring and listing fixes), which implies a read-only analysis, but it does not explicitly state that no files are modified, nor does it describe any side effects or prerequisites (e.g., whether the path must exist or be a git repo). The core behavior is clear, but transparency is incomplete.

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 sentences with zero filler. The first sentence front-loads the purpose, scope, and output; the second is a concise input instruction. Every word earns its place.

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?

Given a single required parameter and no output schema, the description covers the essential information: what the tool checks, what score range to expect, and that fixes come ordered. It could be more explicit about the exact return format or error behavior, but for this simplicity it is adequately complete.

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%: the path parameter is fully documented as 'Absolute or relative path to the repository root'. The description only repeats this instruction ('Pass the repo root path') without adding new meaning, so the schema already carries the semantic weight.

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 clearly states the action ('scores'), the resource ('a repository's Claude Code setup'), and enumerates the specific components (CLAUDE.md, .claude/agents, .claude/skills, hooks in settings.json, .mcp.json, .gitignore). It also specifies the output (0-100 score and ordered fix list). This fully distinguishes it from siblings like scaffold_agent and hook_recipes.

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 gives clear context: use this when you want to audit a repository's Claude Code setup and get a prioritized list of fixes. It includes an explicit input instruction ('Pass the repo root path'). It does not explicitly state when not to use it, but the distinct purposes of sibling tools make selection straightforward.

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