clean_tabular_data

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

With no annotations, the description carries the full behavioral burden. It discloses the three transformations but says nothing about whether rows are dropped during deduplication, whether the original dataset is preserved, what happens on malformed input, or what the tool returns. For a data-mutating sanitizer, that is a meaningful gap.

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?

A single dense sentence with no filler, and the operations are front-loaded in the order an agent would care about them. Nothing is wasted.

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?

The tool is simple (one parameter, no nested objects), but there is no output schema and the description never explains what cleaned output looks like or how it is returned. An agent would know what the tool does but not what to expect back, leaving a modest 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?

There is only one parameter and schema description coverage is 100%, so the schema already documents 'Raw CSV or JSON dataset'. The description's mention of 'CSV and JSON' merely echoes the schema and adds no format, encoding, or size details. Baseline 3 applies.

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 names three specific operations (normalizes, deduplicates, strips injection payloads) and a concrete resource type (untrusted CSV and JSON tabular datasets). This is far more than a restatement of the name. It does not explicitly contrast itself with siblings like json_repair, but the 'tabular' scope and security-oriented operations already differentiate it reasonably well.

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?

There is no statement of when to use this tool versus alternatives such as json_repair or regex_oracle, nor any prerequisite conditions. The word 'untrusted' hints at a security-cleaning context, but the agent must infer that on its own.

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