todos

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It fails to indicate that "implement" mode modifies files destructively, that operations are LLM-powered (per schema), or what return format to expect. Only "prioritization options" hints at capabilities without explaining 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 single sentence is efficiently structured and front-loaded with the core action and target. However, for a 9-parameter dual-mode tool, it may be overly terse at the expense of necessary behavioral context, though it avoids fluff.

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 9 parameters, dual operational modes (read vs destructive write), and zero annotations, the description is insufficient. It omits critical safety warnings for "implement" mode, doesn't clarify output expectations, and fails to bridge the gap between the simple summary and the complex schema options.

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?

With 100% schema description coverage, the baseline is 3. The description adds minimal semantic value—"prioritization options" loosely maps to `difficulty` and `groupBy` parameters, but doesn't explain syntax, defaults (e.g., maxResults differs by action), or the conditional nature of params like `dryRun` (implement-only).

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 uses specific verbs ("Find or implement") and identifies the exact resource ("TODO/FIXME markers"), clearly distinguishing this from general refactoring siblings like `refactor_helper` or `find_and_fix`. However, it doesn't explain what "implement" entails (LLM-powered fixes) or how it differs from the `find_and_fix` sibling.

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 `find_and_fix` or `suggest_refactoring`, nor does it explain when to choose "find" versus "implement" action modes or prerequisites like workspace setup.

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