delegate_review

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

With no annotations, the description carries the transparency burden. It discloses 'read-only' behavior, which is a key safety trait, and prescribes a verification workflow ('Claude must verify each material finding'). It does not detail external model quirks or error behaviors, but for a read-only review tool this is sufficient.

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 concise sentences with front-loaded purpose and clearly scoped usage examples. Every sentence earns its place with no filler.

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?

The tool has moderate complexity (5 parameters, output schema) and the description covers the primary use cases and safety constraints. It does not explain the difference from delegate_analysis, but the output schema and clear purpose make it complete enough for correct invocation.

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 only 40% (only task and diff_or_context are described). The description adds no parameter-level guidance, leaving reasoning_effort and max_output_tokens to be inferred from names/enums. The description does not compensate for the low coverage.

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 states a specific verb and resource: 'Request a read-only code review from one external model.' It clearly distinguishes from sibling tools like delegate_patch and delegate_analysis by specifying 'read-only code review' and 'one external model.'

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?

The description provides explicit use cases: 'correctness, regression, security, concurrency, data-loss, or missing-test review.' It also instructs that Claude must verify each material finding, but it does not mention when not to use the tool or name alternatives, so it falls short of a 5.

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