review_changes

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds meaningful behavioral context beyond these: the evidence is immutable, fenced as untrusted data, and includes all change types without truncation. This meaningfully clarifies the tool's safety boundary and execution model. No contradiction with annotations.

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 two sentences with no filler. The first sentence front-loads the core action and object; the second adds the important scope guarantee of including all change types without truncation. Every phrase 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 complex tool with 13 parameters, zero required parameters, no output schema, and open-world side effects, the description gives a solid high-level summary but does not mention how results are retrieved, whether the operation is asynchronous, or what the caller receives back. The schema and annotations are rich, but the description alone leaves some workflow ambiguity for an agent.

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 92%, so the schema already documents nearly all parameters well. The description does not add per-parameter meaning, though phrases like 'untrusted evidence boundary' loosely relate to maxPromptBytes and maxArtifactBytes. With high schema coverage, a baseline of 3 is appropriate.

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 action — capture a complete Git evidence artifact and start independent read-only provider reviews — and names the exact resource (Git changes) and scope (committed, staged, unstaged, untracked). It clearly differentiates this from sibling single-provider request tools by emphasizing multi-provider, evidence-based review.

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 implies the use case: review repository changes with multiple independent providers. However, it does not explicitly state when to use this tool over alternatives such as validate_with_models or the per-provider request tools, nor does it provide exclusions or conditions for choosing a different tool.

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