check_git_safety

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

No annotations exist, so the description carries the burden. It clearly implies a read-only scan but never explicitly states non-destructive behavior, whether it requires a git repo, or what happens when no files are supplied. It also doesn't mention output format or exit status, which agents need to interpret results.

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?

A single, front-loaded sentence that immediately states the action, target, and specific checks. Efficient with no filler, and the usage hint is appended naturally. 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?

For a simple tool with zero required parameters and no output schema, the description is adequate: it tells what it scans and when to use it. It only lacks clarity on the result format (e.g., list of issues, exit code) and whether it's safe to run repeatedly, but these are secondary given the tool's simplicity.

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%, with both parameters already described as optional with clear meanings. The description adds no extra nuance about how files interact with 'staged/modified' or what happens if project_path is omitted. Baseline of 3 is appropriate given the schema already documents both params.

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 action ('Scan') with clear targets (target or staged files) and enumerates three concrete checks (conflict markers, secrets, debug statements). It differentiates from siblings like run_security_audit by naming specific scan types, though it doesn't explicitly contrast with run_staged_checks which could overlap.

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?

Provides a clear temporal usage hint ('Use before git commit') but offers no guidance on when to use this vs. sibling tools like run_staged_checks or run_security_audit. The 'or' in 'target or staged files' is ambiguous about precedence. Exclusions or alternatives are not addressed.

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