Fix loop

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

Annotations already flag mutating/destructive behavior, and the description adds critical context: patches are applied only when allowApply=true and client supports MCP sampling, and every action is reported. This is exactly the kind of behavioral detail that goes beyond the raw flags.

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 about 75 words, front-loaded with the core loop concept, and every sentence contributes procedural detail. It is compact without sacrificing essential information.

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 the complexity of a 7-parameter orchestration tool and no output schema, the description covers the workflow and fallback but does not explain return value structure or the exact behavior of stopOnFirstSuccess/timeoutMs. The gaps are noticeable but the core flow is sufficiently described.

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 schema documents checks, allowApply, projectPath, and taskDescription, but not timeoutMs, maxIterations, or stopOnFirstSuccess. The description adds meaning for maxIterations ('up to maxIterations') and allowApply, but leaves timeout and stop behavior implied. With 57% coverage, the description provides moderate compensation.

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 the tool runs a 'controlled verify→analyze→fix loop', a specific verb+resource that distinguishes it from sibling single-step tools like run_project_checks or apply_patch. It conveys the core orchestration purpose immediately.

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 explains the loop mechanics: runs checks, analyzes on failure, applies patches conditionally, and repeats until maxIterations. It also describes the fallback advisory when sampling is unavailable. However, it does not explicitly contrast with alternate tools, though the context implies using this for multi-step automation.

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