check_claudemd_drift

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

Annotations already provide readOnlyHint, destructiveHint, idempotentHint. Description confirms read-only but adds no significant behavioral details beyond the inferred return JSON structure. Does not describe side effects or error behavior, which is acceptable given annotations.

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 wasted words. First sentence declares purpose and scope, second provides alias and output format. Information density is high and immediately useful.

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?

No output schema exists, but description defines the return JSON structure. Parameters are fully covered. The tool is simple (2 optional params) and the description sufficiently explains its role alongside siblings like audit_config and detect_drift. Could mention error scenarios but not critical.

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 coverage is 100%, so baseline 3. Description adds default behavior: 'default: auto-detect' for config_files and 'default true' for fix_suggestions, which the schema does not include. This adds meaningful usage guidance.

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?

Description uses specific verb 'detect drift' and lists exact resources (CLAUDE.md, AGENTS.md, .cursorrules) and issues (dead path references, non-existent MCP tools, missing skills/commands, oversized sections). It distinguishes from sibling 'audit_config' by stating it's a convenience alias with drift_only=true.

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?

Explicitly states it's a convenience alias for 'audit_config { drift_only: true }', guiding when to use this tool versus the more comprehensive audit. Read-only nature is noted. Lacks explicit when-not-to-use but provides sufficient context.

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