recommend_changes

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

Reinforces readOnlyHint from annotations and adds honest caveats about detection confidence and taste calls, providing additional behavioral transparency beyond 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?

Four sentences that efficiently convey purpose, usage, and caveats without fluff. Front-loaded with the core action.

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?

Given output schema exists, return values don't need description. The tool has low complexity with one parameter; description covers main aspects but lacks error conditions or prerequisites, which is acceptable for a read-only analysis tool.

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?

The description mentions 'target fingerprint' which maps to the 'target_style' parameter, but does not explicitly describe the parameter format or provide examples. With 0% schema coverage, some compensation exists but not full.

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?

Clearly states the tool diffs current project against target fingerprint and returns an EditPlan with specific dimensions. Verbs and resource are explicit, and the distinction from 'apply_changes' is made.

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 it is read-only and instructs to surface reasons to user for approval then call apply_changes, providing clear when-to-use and follow-up step.

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