Skip to main content
Glama

Data Quality Gate - deterministic post-scrape cleaner + verdict

by io.github.aidatatools-dev

clean_scraped_data

PAID TIER, CALLED FROM A FREE ENDPOINT -- READ THIS FIRST: this tool does NOT return your cleaned data, and its response has NO data key. It returns {"status": "payment_required", "what_we_found_in_your_data": {...}, "get_the_repaired_data": {...}}. Do not treat its output as cleaned data and do not write it back into your dataset. WHAT YOU GET HERE, FREE: an exact inventory of the defects in YOUR data -- which repair rules would fire, how many values each would change, and which cases cannot be repaired safely and need your decision. HOW TO GET THE REPAIRED DATA: make the one call named in get_the_repaired_data -- POST https://www.aidatatools.dev/api/clean, $0.04 via x402, no account, no API key, no signup. That response body IS the cleaned dataset, in the shape you posted it. WHY THE SPLIT: detection is free on this endpoint and always has been (check_dataset_quality reports the same defects). The repaired artifact is the paid product, because it is re-bought on every extraction run rather than cached like a verdict. WHAT THE PAID CALL DOES: removes leftover HTML tags and entities, decodes mojibake ('Café' -> 'Café'), strips invisible characters (zero-width, BOM, soft hyphen), normalises non-breaking spaces and trims values -- across nested objects and arrays too. 100% deterministic, no LLM: the same input always yields byte-identical output, and cleaning twice equals cleaning once. It repairs how data was ENCODED, never what it SAYS: masked placeholders ('N/A', 'None'), near-duplicate rows and failed extractions ('access denied', 'captcha', which mean that record must be re-scraped) are reported with a proposal, never silently deleted or rewritten. The full boundary -- 7 rules applied automatically, 5 needing an explicit opt-in, 8 only ever reported -- is at GET https://www.aidatatools.dev/api/clean.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
optionsNoAll optional. Every default is the safe one: with no options, the row count, every value's type, and the schema are all guaranteed unchanged.
rawJsonYesThe scraper output: a JSON array of row objects, a single object, or a CSV/plain-text string. The format is detected and the output mirrors the shape you sent.

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and excels: it discloses the response shape (no data key), the deterministic/no-LLM nature, the explicit list of repairs (HTML tags, mojibake, invisible chars), and the boundary of what is repaired vs. reported rather than silently changed. It also reveals cost/authentication requirements for the paid endpoint, which is valuable behavioral context beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Though long, the description is densely informative and structured via headers and a prominent warning. Every section ('WHAT YOU GET HERE', 'HOW TO GET THE REPAIRED DATA', 'PROVENANCE', 'PAID CALL BEHAVIOR') earns its place, and the front-loaded warning prevents misuse. The structure aids scannability despite the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, but the description fully compensates: it explains the exact output structure, the fields returned, the calling flow for the paid service, the deterministic nature, and the repair/report boundary. It also preempts common mistakes (e.g., writing output back into the dataset) and provides a URL for the full rules. This is a complete picture for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters (rawJson and options with detailed defaults/enums). The main description does not add parameter-level semantics beyond what the schema provides; it focuses on tool behavior. This meets the baseline 3 for high schema coverage, but does not exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool does NOT return cleaned data, instead returning an inventory of defects and instructions for the paid repair endpoint. The verb 'returns' plus the precise resource ('exact inventory of the defects in YOUR data') makes the purpose unambiguous, and the contrast with the paid call distinguishes it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly explains when to use this free endpoint (detection, no account needed) versus the paid call for repaired data, and explicitly names check_dataset_quality as reporting the same defects. It also provides a concrete alternative path ('make the one call named in get_the_repaired_data') and a rationale for the split.

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

All Data Quality Gate - deterministic post-scrape cleaner + verdict toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation2/5

check_dataset_quality is clearly distinct, but clean_scraped_data and clean_scraped_data_audited are nearly identical in behavior, differing only in the paid endpoint and audit trail. An agent would be uncertain which to call, making the boundaries between the two cleaning tools unclear.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (check_dataset_quality, clean_scraped_data, clean_scraped_data_audited), with the last adding an '-audited' modifier. There is no mixing of conventions or irregular naming.

Tool Count4/5

Three tools is a reasonable number for a focused quality-gate server, placing it within the typical 3-15 range. However, two of the three are near-duplicates, reducing effective diversity, so it is slightly padded rather than perfectly scoped.

Completeness2/5

The server allows quality checking and defect inventory, but the actual cleaning is delegated to external paid endpoints, so an agent cannot complete a cleanup task within the MCP framework. Missing a tool to actually retrieve or apply cleaned data creates a significant gap.

Resources