Skip to main content
Glama

Read dataset records

read_dataset
Read-onlyIdempotent

Call this to read a dataset's records, a page at a time: the latest version and 50 records unless you say otherwise, oldest first. Get the slug from list_datasets, the fields from dataset_info. For what is happening now (is this MCP server up, is this provider having an incident), pass order newest, and where to keep the records of one server, host or provider — no key needed for a free dataset. total is how many records the version holds and next the offset of the next page (null after the last; with where, offsets count matching records). A version never changes, so pages are stable. A free public dataset reads with no key (up to 120 pages an hour per network); signed in, the bytes count toward your operator's free 50 GB a month. A paid dataset answers with its price instead (buy_dataset buys it with credits, buy_dataset_with_usdc from a wallet). An unknown slug or version answers not found. With an agent key, query_dataset runs SQL and dataset_manifest gives a whole version's files.

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": {
      "slug": "<slug>"
    },
    "name": "read_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesthe dataset project's slug, as list_datasets gives it (e.g. agent-api-observatory): 3–60 lowercase letters, digits and dashes
limitNorecords on the page, 1–200; left out, 50
orderNonewest: the most recently added records first; left out, oldest first
whereNokeep only records whose field equals the value, e.g. {"server": "github"}; end the value with * to match a prefix ({"host": "api.openai*"}). Up to 4 fields, names from dataset_info
offsetNorecords to skip, from 0 (the answer's next is the next page's offset); left out, 0
versionNothe version to read, from 1; left out, the latest

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / order
      Added value: +{
      +  "description": "newest: the most recently added records first; left out, oldest first",
      +  "enum": [
      +    "oldest",
      +    "newest"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / where
      Added value: +{
      +  "additionalProperties": {
      +    "maxLength": 190,
      +    "type": "string"
      +  },
      +  "description": "keep only records whose field equals the value, e.g. {\"server\": \"github\"}; end the value with * to match a prefix ({\"host\": \"api.openai*\"}). Up to 4 fields, names from dataset_info",
      +  "propertyNames": {
      +    "pattern": "^[A-Za-z_][A-Za-z0-9_.-]{0,63}$",
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
  2. Changed4 schema fields changed
    • addedInput schema / properties / limit / description
      Added value: +"records on the page, 1–200; left out, 50"
    • addedInput schema / properties / offset / description
      Added value: +"records to skip, from 0 (the answer's next is the next page's offset); left out, 0"
    • addedInput schema / properties / slug / description
      Added value: +"the dataset project's slug, as list_datasets gives it (e.g. agent-api-observatory): 3–60 lowercase letters, digits and dashes"
    • addedInput schema / properties / version / description
      Added value: +"the version to read, from 1; left out, the latest"
  3. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, non-destructive, closed-world, but the description adds material context that annotations cannot: rate limits (120 pages/hour per network), auth-dependent billing (50 GB/month signed in, no key for free datasets), paid datasets returning price instead of records, and not-found behavior for unknown slug/version. It also explains version immutability and page stability.

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?

Front-loaded correctly and information-dense, but the paragraph is a single run-on where the order=newest advice is jammed together with the where clause ("pass order newest, and where to keep the records of one server, host or provider — no key needed for a free dataset"), which is hard to parse. Splitting the filtering, pricing and pagination material into separate sentences would cost nothing and gain clarity.

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?

No output schema exists, yet the description explains the two return fields an agent needs to page (total is the record count, next is the next offset, null after the last page). Combined with auth/pricing, error behavior and sibling escape hatches, an agent can call this correctly without further information.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3 and the schema already documents limit, order, offset, version, where and slug. The description adds real meaning on top: where the slug comes from, that where restricts to one server/host/provider with prefix matching, and that offsets count matching records when where is used. It does not restate the numeric bounds, which the schema handles.

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?

"Call this to read a dataset's records, a page at a time" gives a specific verb plus resource plus the pagination model in the first clause, and the defaults (latest version, 50 records, oldest first) are stated immediately. It is clearly distinguishable from list_datasets, dataset_info, query_dataset and dataset_manifest, which are all named for contrast.

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?

Explicit routing conditions: use order=newest "for what is happening now"; use query_dataset for SQL and dataset_manifest for whole-version files "with an agent key"; use buy_dataset / buy_dataset_with_usdc when a paid dataset answers with its price. It also states prerequisite sources for inputs (slug from list_datasets, field names from dataset_info).

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.