Skip to main content
Glama

x402 Tool Shop

CSV Preflight Check

csv_preflight
Read-only

CSV preflight: validate a CSV before import and find every load error first. Detects the delimiter, line endings, BOM and encoding damage, header problems (blank or duplicate names), rows with the wrong field count (with line numbers), unterminated quotes, duplicate rows, and per-column type, empty rate and mixed or ambiguous values. Returns ready true/false plus every issue. POST JSON {csv}, up to 1.5 MB. Price: $0.005 USDC per call (x402). Free sample: call free_sample with tool="csv_preflight".

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "csv_preflight"
  }
}

Input Schema

NameRequiredDescriptionDefault
csvNoThe CSV text (up to 1.5 MB)
delimiterNoOptional: ',', ';', 'tab' or '|' (detected if omitted)
has_headerNoOptional: whether row 1 is a header (detected if omitted)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the transport ('POST JSON {csv}'), a hard input cap (1.5 MB), the return shape ('ready true/false plus every issue'), and a per-call price under x402. Cost and payload limits are exactly the kind of operational context annotations cannot express.

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

Conciseness4/5

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

Purpose and the 'ready' outcome are front-loaded, then detection categories, then transport/limits/pricing. The detection enumeration is long but each item is distinct information; only the final sample/pricing sentence could be tightened.

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

Completeness4/5

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

With no output schema, the description carries the return burden and does provide 'ready true/false plus every issue', size limits, and cost, which is enough to decide and call correctly. The shape of individual issue objects (fields, line-number format) is not described, which is the main remaining gap for a diagnostic tool.

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 all three parameters (csv, delimiter, has_header) are already documented, including the auto-detection fallbacks. The description only restates the 1.5 MB cap and that csv travels in the JSON body, adding little semantic depth beyond the schema.

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?

Opens with a specific verb and resource ('validate a CSV before import') and then enumerates exactly what it inspects: delimiter, line endings, BOM/encoding damage, header problems, field-count mismatches with line numbers, unterminated quotes, duplicate rows, and per-column type stats. An agent knows precisely what class of tool this is without opening the schema.

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

Usage Guidelines4/5

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

'Before import' and 'find every load error first' establish the usage timing clearly. It also names the free_sample sibling with a concrete invocation (tool="csv_preflight") for a no-cost trial, though it stops short of stating when a different tool would be preferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources