Fix the tracker

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

Beyond the destructiveHint annotation, the description discloses that the tool takes a backup, performs one write and one undo step, requires the user's yes, and supports undo_last_write. It also explains the version-check refusal behavior, which is important for a destructive write tool.

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 front-loaded with purpose and then safety workflow, and every sentence earns its place. The enumeration of fixes is dense but useful for an agent deciding whether this tool will make the needed changes.

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 destructive multi-fix mutation with an output schema, the description covers the essential context: what gets fixed, the approval protocol, backup and undo behavior, and version-conflict handling. Nothing critical is missing 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 coverage is 100%, so the baseline is 3, but the description adds meaningful workflow semantics for dry_run, confirm, and expected_version that the schema alone does not fully convey. It does not add much beyond the schema for rows and kinds, which keeps it from a 5.

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 ('Fix the fixable issues check_tracker found') and enumerates the exact repairs performed. It clearly differentiates this tool from check_tracker, which detects issues, and undo_last_write, which reverses writes.

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?

It gives explicit workflow guidance: use after check_tracker, call with dry_run=true first unless the client shows its own confirmation dialog, then repeat with the confirm token after user approval. It also states that writes are refused if expected_version no longer matches.

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