SwishrJobs

CSV preflight: find what will break the import

submit_csv_preflight

Idempotent

Check a CSV before it is imported. Reports ragged rows, duplicate and empty column names, blank and duplicate rows, per-column type drift and column profiles, each with the row number a spreadsheet would show. Choose this when you have a CSV file and want the problems listed with the row numbers a spreadsheet shows: ragged rows, duplicate or empty column names, blank and duplicate rows, and per-column type drift. Do not choose this when you want the file fixed rather than diagnosed (use csv-clean), when you want a module that validates records in your own pipeline (use data-validation-module), or for a binary workbook such as xlsx, which this service cannot read. Example requests: Check this CSV for problems before I import it into Postgres. | Why does my CSV import fail? Here is the file. | Preflight a customer data export and tell me which rows are malformed.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "inputs": "<inputs>",
      "authorized_by": "<authorized_by>"
    },
    "name": "submit_csv_preflight"
  }
}

Input Schema

Name	Required	Description
`inputs`	Yes
`quote_id`	No	The quote_id returned by POST /v1/jobs. Required to authorize a priced capability; the service rejects a priced job that does not name the quote it issued.
`authorized_by`	Yes	Identifier of the human or agent authorizing this job.
`accepted_price`	No	The amount accepted, exactly as quoted (for example "5.00" or 5). Checked against the stored quote, so a price that moved between quote and authorize is refused rather than silently absorbed. Optional, but sent to make the acceptance explicit.

Output Schema

Name	Required	Description
`quote`	No
`state`	Yes
`job_id`	Yes
`artifacts`	No
`access_token`	No	Per-job credential. Present it as the X-Job-Token header to read the job or list it. Keep it; it is the only credential for this job.
`verification`	No	Independent verification. verification.ok = false means the job failed, not a partial success.
`capability_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond the annotations it discloses real behavioral boundaries: it diagnoses rather than repairs, and the service cannot read binary workbooks such as xlsx. What it omits is the job/pricing flow implied by quote_id and accepted_price, so an agent learns about the quote handshake only from the schema, not the description.

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

Conciseness3/5

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

The when-to-use sentence largely re-lists the same findings already enumerated in the opening sentence ('ragged rows, duplicate and empty column names, blank and duplicate rows, per-column type drift' appears twice), so a meaningful share of the text is redundant. The ordering is good — capability first, alternatives later — but the duplication costs it.

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 an output schema present, the description needn't explain return values, and it covers scope, exclusions, and example phrasings well. The only gap against a 4-parameter priced capability is the absence of any mention of the quote/authorization step, though the schema documents it.

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 75%, with content, quote_id, and accepted_price all documented in-schema, so the baseline is 3. The description adds no parameter-level detail — delimiter support and the 1 MB limit live only in 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?

The description names a specific verb and resource ('Check a CSV before it is imported') and enumerates exactly what is reported: ragged rows, duplicate/empty column names, blank and duplicate rows, type drift and column profiles. It also names the sibling tools it is not (csv-clean, data-validation-module), so an agent can distinguish it without opening any schema.

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?

It gives explicit selection criteria plus explicit exclusions: not for fixing the file (use csv-clean), not for pipeline validation modules (use data-validation-module), not for xlsx binaries. Three example requests anchor the intent in realistic phrasing, leaving nothing to inference.

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

All SwishrJobs tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?