Skip to main content
Glama

Describe a live data source

live_data_source
Read-only

Inspect a live data source’s input/output schema and sample runs before using it, so you can format inputs correctly and confirm expected results.

Instructions

Describe one live data source: its input_schema (what live_data passes as inputs), output_schema and recorded sample runs. About a second; free. Read it before a source's first run here. NOTHING IS CONFIGURED FOR THIS METHOD on this machine, so every call will fail. A key in one of APIFY_TOKEN, BRIGHTDATA_API_TOKEN, NIMBLE_API_KEY, OXYLABS_WEB_API_KEY turns it on: see load_env.

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": {
      "name": "<name>"
    },
    "name": "live_data_source"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe source's name, as `live_data_sources` lists it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover read-only and open-world status, so the description's added value is the latency/cost profile ("About a second; free") and the blunt operational caveat that nothing is configured and every call will fail without one of the listed API tokens. That is unusually candid and actionable. The only gap is that it doesn't say what a sample-run record looks like or how many runs are returned.

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

Conciseness5/5

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

Front-loads the payload contents, then cost, then the use-before-first-run rule, then the blocker and its fix. Four short sentences with no filler; even the token list is compressed into one line of essential setup information.

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, and the description compensates by naming the three things returned. For a single-parameter read tool this covers what the agent needs: what it gets back, what it costs, when to call it, and why it might currently fail.

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?

Only one parameter exists and schema coverage is 100%, so the schema already explains that `name` is the source name drawn from `live_data_sources`. The description restates that linkage but adds no format, casing, or validation detail beyond it, making this baseline-level performance by design.

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 and resource ("Describe one live data source") and enumerates exactly what the response contains: input_schema, output_schema, and recorded sample runs. It also implicitly separates itself from `live_data` (the runner) and `live_data_sources` (the lister) by tying the `name` argument to what `live_data_sources` lists.

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?

Gives an explicit timing rule ("Read it before a source's first run here"), which routes the agent to this tool before invoking `live_data`. It goes further than most guidelines by stating the current failure condition and naming the remediation path (`load_env` plus the specific token variables).

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