review

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, indicating safe, idempotent read. The description adds that it is deterministic and 'no LLM', and details what the audit includes (blast radius, risk tier, etc.), which goes beyond annotations. No contradictions.

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?

The description is information-dense but well-structured: starts with primary purpose and key trait ('Deterministic, no LLM'), lists outputs, then usage context and sibling pointers. No unnecessary words; every sentence adds value.

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, so the description must convey return value. It does so comprehensively: symbols, blast radius, risk tier, covering-test count, flags, tests_to_run, checklist. Parameters are optional and self-explanatory from schema. The description is complete for safe, effective use.

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% (all three parameters described in schema). The description adds context by mentioning 'base_ref' as the diff base, enhancing understanding beyond the schema alone.

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 it is a 'Deterministic diff AUDIT' and enumerates specific outputs (symbols changed, blast radius, risk tier, covering-test count, flags like public_api_changes, untested_changes, high_risk, tests_to_run, checklist). It distinguishes itself from siblings by positioning as the write-side complement to `plan` and pairing with `diagnostics` and `review_diff`.

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 'Use AFTER editing, before finishing.' Provides context on when to use relative to siblings: 'The write-side complement to `plan`; pair with `diagnostics` and `review_diff`.' This gives clear guidance on tool selection.

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