SwishrJobs

CSV deduplicate: group duplicate rows and return a deduped file

submit_csv_deduplicate

Idempotent

Find duplicate rows in a CSV, group each set with the row numbers it appears on, and return a deduplicated file keeping the first occurrence. Choose this when a CSV has repeated rows and you need them collapsed and named: the report groups each duplicate set with its row numbers and the delivered file keeps one copy of each row. Do not choose this when duplicates must be judged on a specific key column rather than the whole trimmed row. Example requests: Remove duplicate rows from this CSV and tell me which were duplicates. | How many duplicates are in this CSV file? | Give me a deduplicated copy of this CSV.

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_deduplicate"
  }
}

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.

AddedNov 3, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=false; the description reinforces this with 'keeping the first occurrence' and clarifies that a report of grouped duplicates is produced alongside a delivered file. It adds real behavioral value beyond the hints, though it says nothing about job/pricing flow (quote_id, accepted_price) or how large inputs are processed.

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?

Front-loaded with the core action, then the selection rule, then the exclusion, then example utterances that help with triggering. The grouping/row-number behavior is restated twice ('group each set with the row numbers' and 'the report groups each duplicate set with its row numbers'), which is mild redundancy but not bloat.

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 need not explain return values, and the when/when-not framing covers the main decision risk. It omits the priced-capability/job authorization context that the required quote_id implies, which is the only notable gap for a 4-parameter tool with nested inputs.

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 coverage is 75%, so the schema already documents content limits, quote_id and authorized_by. The description adds only the dedup semantics of what counts as a duplicate (whole trimmed row vs. key column), and never mentions authorization or pricing parameters, so it does not meaningfully compensate beyond the schema baseline.

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?

States a specific verb plus resource and outcome: find duplicate rows, group each set with the row numbers it appears on, and return a deduplicated file keeping the first occurrence. It also distinguishes scope from the key-column variant, so an agent can tell it apart from record-level dedup siblings without opening a 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?

Explicitly gives a when-to-use condition (repeated whole rows that must be collapsed and named) and a when-not-to-use condition (duplicates judged on a specific key column rather than the whole trimmed row). The exclusion is clear, but the alternative sibling (e.g. submit_record_deduplication) is never named, leaving a small inference step.

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?