clean_data

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

With no annotations, the description carries the full burden and does notable work: it flags the tool as Paid (a critical operational trait) and states the return contains 'cleaned output plus what was fixed' despite there being no output schema. It stops short of disclosing auth requirements, size limits, or failure behavior, but the cost and output disclosures are substantive.

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?

Three dense sentences, zero filler, and the core value proposition plus the paid flag are front-loaded before the mode breakdown. A model can parse it in one pass.

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 two-parameter tool with no output schema, the description explains both inputs' purpose and the shape of the return, including the per-mode behavior. Input size limits, error handling, and the cost amount are unstated, which is the only material gap.

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% and the enum already names the five modes, so baseline is 3. The description exceeds that by explaining what each mode does (json parse+pretty+validate, csv RFC4180 normalization, date ISO-8601), which tells the agent which mode to select rather than just the legal values.

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?

States a specific verb+resource (clean messy data) and enumerates exactly what it does for each of the five modes. None of the siblings (check_domain, summarize_url, advise_decision, etc.) overlap in function, so no differentiation is needed.

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?

'Send messy data; get it back clean' implies the trigger condition, and 'Paid' signals a cost consideration, but there is no explicit when-not guidance or named alternative. The mode list helps an agent pick a mode, which is partial usage guidance.

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