guard_diff_audit

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

Annotations already declare idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds that a verdict is computed against thresholds, but it never says where thresholds come from, whether the call can fail or block, or why readOnlyHint is false for what reads like a pure analysis operation.

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?

One short sentence with no filler, and the diff target is front-loaded before the outputs. It is dense to the point of being cryptic ('numstat stats + verdict vs thresholds'), but nothing is wasted.

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?

An output schema exists, so return values need not be described, and the single optional parameter is covered. Still missing is how thresholds are configured or overridden and what the verdict values mean, which matters for an auditing tool whose whole purpose is producing a pass/fail judgment.

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 0% for the single `baseline` parameter, so the description carries the burden. It does so usefully by explaining that baseline is a git ref and that HEAD is the implicit default, which is meaning the bare nullable string schema does not convey.

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 output: it diffs against HEAD or a baseline ref, produces numstat statistics, and yields a verdict compared against thresholds. That distinguishes it reasonably from siblings like guard_status or guard_verify, though 'audit' and 'thresholds' remain jargon without a stated meaning.

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?

There is no guidance on when to call this versus guard_verify, guard_status, or guard_preflight, nor any stated prerequisite. The only implied usage is 'when you want a diff-based verdict', which is thin for a family of twelve guard_* tools.

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