Auto Diagnose

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

Annotations already indicate destructive behavior (destructiveHint=true). The description adds that the tool autonomously iterates until a target score is reached and performs 'safe-fix' actions, which gives some additional behavioral context beyond the annotation. However, it does not detail what constitutes a safe-fix, potential side effects, or whether changes are reversible, so it only partially discloses behavior.

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 a single, succinct sentence that front-loads the core concept ('Autonomous self-healing') and clearly outlines the process flow with an arrow sequence. There is zero fluff, and every chunk of the description conveys essential information about the tool's behavior. This is an excellent model of conciseness.

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?

Despite being a complex, destructive, autonomous tool with three parameters and no output schema, the description provides minimal context. It does not explain what a safe-fix entails, how the score is computed, whether it modifies files in the repository, or what happens if maxIterations is exceeded. For an agent to safely invoke this tool, more operational details are necessary, making the description incomplete.

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 references 'target score' and 'iterate', which loosely map to targetScore and maxIterations parameters. This adds some meaning beyond the schema, where only path has a descriptive comment. However, it does not explicitly explain these parameters, their defaults, or how they interact. With schema coverage at 33%, the description should provide more details but only hints at them.

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 clear purpose: autonomous self-healing through a defined cycle of diagnose, safe-fix, re-score, and iterate. This implies both diagnosis and correction, distinguishing it from sibling tools like full_diagnose which likely focuses on diagnosis alone. However, it could be more explicit about the resource (code repository) and the exact actions taken during fixing.

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 no guidance on when to use this tool versus alternatives like full_diagnose or verify_all. It does not mention conditions, prerequisites, or scenarios where this tool is preferable. An agent is left to infer usage from the name and partial description, which is insufficient.

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