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

No annotations are provided, so the description carries the burden. It openly states the tool will analyze data and point to another tool, implying no direct mutation. It could add detail on output format or what happens when no problem is found, but the core diagnostic behavior is clearly disclosed.

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?

Two short sentences with no waste. The user-facing trigger is front-loaded and the behavior is stated immediately.

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 simple single-input diagnostic tool with no output schema, the description explains what it does and what it returns at a high level (a diagnosis and a pointer to a fixer). It does not enumerate possible output details, but it is sufficient for an agent to select and invoke the 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?

There is one parameter with 0% schema description coverage, so the description must compensate. 'Show me the problematic data' clearly maps the `input` parameter to the data to be diagnosed, giving it meaning beyond the generic schema name.

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 diagnostic purpose: accept problematic data, identify likely formatting problems, and recommend a fixer tool. It distinguishes itself from sibling normalization/detection tools by being the diagnostic router rather than the fixer, though it does not name them.

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 establishes a clear trigger ('Something isn't working? Show me the problematic data') and indicates that the tool will route to a deterministic fixer. It does not explicitly state when not to use it or name alternatives, but the routing behavior implies that known, specific issues should go to the sibling fixer tools.

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