review_git_diff

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

With no annotations, the description carries the full burden, and it does add real value by disclosing the decision model (BLOCK_MERGE_CRITICAL through CLEAN_APPROVAL) and that it returns a formatted comment rather than posting one. However, it omits operational traits an auditor would need: whether external services are contacted, diff size limits, latency, or determinism.

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 dense sentences, front-loaded with the action and followed by the return contract; nothing is redundant. The enum list is verbose but functional, and the jargon-heavy phrasing is the only mild drag.

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, and the description compensates by naming the primary return fields and the full decision vocabulary, which is the main thing an agent needs. It falls short only on the failOnSeverity/threshold relationship and any practical limits on diff size or cost.

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% and both parameters are fully documented in-schema, so baseline 3 applies. The description never mentions failOnSeverity, which materially changes which mergeDecision tier fires — a missed opportunity to explain how the threshold interacts with the returned decision.

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 verb and resource — auditing a unified git diff (.patch / git diff / PR payload) — and enumerates concrete outputs (prRiskScore, mergeDecision tiers, findings, formatted review comment). It implicitly distinguishes itself from scan_diff_for_secrets by calling itself a 'full multi-gate' audit, but never names siblings explicitly.

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?

Usage is only implied: 'full multi-gate DevSecOps and compliance audit' suggests this is the comprehensive option versus narrower siblings, but there is no explicit 'use this when / use X instead' guidance or stated prerequisites. An agent must infer the routing from wording rather than being told.

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