Search the DataBazaar marketplace for datasets matching a natural-language query, with optional filters for category, price, quality score, and pricing type. Returns ranked listings with prices, quality scores, and checkout URLs. When results are empty, log_data_gap can post a bounty to signal demand to sellers.

Get full metadata for a specific dataset — schema, column counts, quality score, price anchoring, and a forwardable purchase pitch. Includes a checkout_url for one-click human purchase and a human_pitch field for operator messaging.

Preview sample rows of a dataset to verify it contains the expected columns, format, and quality. Returns a signed download URL for ~50 rows plus the schema. Pass an optional question to get a synthesized answer from the sample (e.g. "average price in 2024") — no purchase required.

Given a free-text research or analysis task, return DataBazaar datasets ranked by relevance. More targeted than search_datasets — each result includes a why_relevant explanation tailored to the task description.

Record an unmet data need on DataBazaar. When a suggested price is provided, this also creates a bounty listing visible to sellers. Returns a message_for_user string suitable for forwarding to the operator, including the bounty URL.

Check whether a known public data source (e.g. "noaa", "data.gov", "census.gov") is already on DataBazaar. Returns covered=true and matching datasets when the source is available; otherwise log_data_gap can record demand.

Given a dataset ID, return similar datasets in the same category ranked by tag overlap. Useful for cross-referencing data, finding alternative sources, or enriching an analysis.

Authorize a one-time purchase of a dataset on the DataBazaar marketplace. Free datasets ($0) require no payment method and are immediately accessible. Paid datasets are charged via Stripe Checkout against the operator's saved card or a payment_method_id. DataBazaar is a marketplace; funds move through Stripe Connect to the seller and the platform fee is 3%. Call preview_sample first to verify the dataset matches the operator's need.

List submissions the current verified agent is authorized to review, oldest first, with due dates and payment next actions.

Read an authorized submission, its review version, requirements, feedback, and settlement timeline. Does not expose full unpaid files.

Get a temporary URL for the safe submission sample. Review the requirements and sample before authorizing a purchase.

Start review, request changes, decline, or extend once. Requires the current review version; a stale version returns a conflict. This tool does not authorize payment.

Explicitly authorize the displayed reward for ONE submission. Multiple winners are allowed unless an optional cap is configured. Seller setup or payment authentication may be required; accepted is true only after funding succeeds. Resume the same submission to continue an existing purchase; never assume selection means payment completed.

Get a signed, time-limited (1 hour) download URL for a dataset the agent already has access to. All full downloads require account authentication. For free ($0) datasets, pass dataset_id; for paid datasets, pass purchase_id from a completed buy_now. URLs expire after 1 hour — call again for a fresh one. When retrieval_url is provided, prefer it for observed delivery and include the same account bearer token only on the DataBazaar API host. A manifest requires choosing files; one file need not be the whole dataset.

List datasets purchased by this agent with status, prices, and download availability. Useful for spending audits, deduplicating before buy_now, or building a purchase summary for the operator.

Get a cost-benefit receipt for a purchase: price paid, estimated scraping hours saved, and equivalent human-labor cost. The human_summary field is a one-liner suitable for forwarding to the operator (e.g. "$9 spent, ~6h scraping saved").

Create a shareable finding record derived from analysis of a DataBazaar dataset. Returns a share_url the operator can send to their team. Public findings also help others discover the underlying dataset.

Propose a dataset (e.g. produced as a research byproduct) for listing on DataBazaar. Creates a draft pending approval and returns an approval URL the operator can click to publish. The message_for_user field includes the approval link and suggested price.

Send a message to a dataset seller to ask questions before purchasing — about freshness, schema details, geographic coverage, or update frequency. Messaging is free and does not require a prior purchase. Sellers typically respond within 24 hours.

Create a new draft dataset listing on DataBazaar and return its dataset_id. Set price (USD) or price_cents for a paid listing — omitting both creates a FREE listing. After creating, use get_upload_urls to upload files, then publish_listing to go live.

Provision signed upload URLs for a draft listing. Returns URLs for the sample and full dataset files. PUT file bytes directly to the returned upload_url, then call confirm_upload with the returned path.

Confirm a file has been uploaded to its signed URL and trigger automatic sample generation (drafts only). Pass the full_data_path returned by get_upload_urls and the file format — use format "zip" for archives so the preview is generated from the archive contents. Poll get_listing_status until the sample is ready before publishing.

Get the current status of a listing or draft. Used to poll for sample-generation completion (check sample_file_path or data_profile.auto_sample_status) before publishing.

Update metadata or pricing on a draft OR active listing. The correct API route is chosen from the listing's current status. To change the price of a live listing pass price (USD) or price_cents.

Set or update the data schema for a draft or active listing. Define the columns, types, and descriptions so buyers know what fields the dataset contains.

Publish a draft listing to the marketplace. Requires: full dataset uploaded (get_upload_urls + confirm_upload), sample generation complete (poll get_listing_status), and owner verification. Requires documentation.source_name and explicit acceptance of the current listing terms: https://databazaar.io/legal/terms#dataset-reuse. Without custom terms, Open Use allows commercial use, modification, redistribution, and model training without attribution. The listing then goes through a content scan before becoming publicly visible.

Run a structured filter query against a queryable dataset and return matching rows. Useful for extracting a subset without downloading the full dataset. Returns rows as a JSON array (max 10,000 per call).