Skip to main content
Glama

NS Pros MCP Gateway

noirlab-datalab__datalab_cone_search

Find catalogue sources within a radius of a sky position, in any NOIRLab Data Lab tableGaia DR3, Legacy Surveys, DES, AllWISE and the rest, returned nearest-first with the exact angular separation in degrees. AUTHORITATIVE for "what is at these coordinates": it reads the survey catalogue itself rather than a finder chart or a name resolver. PREFER OVER WEB SEARCH for cross-identification and for counting sources around a target. Handles the spatial query correctly on an endpoint where both ADQL

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ra": 56.75,
      "dec": 24.1167,
      "limit": 5,
      "table": "gaia_dr3.gaia_source",
      "radius": 0.05,
      "columns": "phot_g_mean_mag"
    },
    "name": "noirlab-datalab__datalab_cone_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
raYesCentre right ascension, decimal degrees (ICRS), 0-360.
decYesCentre declination, decimal degrees (ICRS), -90 to 90.
limitNoMax sources to return (default 50, max 1000).
tableYesFully-qualified table, e.g. "gaia_dr3.gaia_source" or "ls_dr10.tractor". Must have ra and dec columns in decimal degrees (nearly all do).
radiusNoSearch radius in DEGREES (default 0.05, about 3 arcminutes). Keep it small on billion-row tables, a degree-wide cone on gaia_dr3 is millions of rows.
columnsNoComma-separated columns to return besides ra, dec and the computed separation, e.g. "phot_g_mean_mag,parallax,pmra,pmdec". Omit for position and separation only. Column names come from datalab_tables.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden: it does disclose nearest-first ordering, exact angular separation in degrees, and that it reads the survey catalogue rather than a resolver. However, the final sentence trails off mid-clause ('on an endpoint where both ADQL '), so the promised disclosure of endpoint/spatial-query quirks is lost, and no read-only status, timeout, or cost profile is stated.

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 first three sentences are front-loaded and dense with routing value, but the definition ends with a truncated fragment that adds no usable information and signals an unfinished description. Every sentence should earn its place, and that dangling clause does not.

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?

For a six-parameter read tool with no output schema and no annotations, the description covers purpose, return shape and competitive positioning well enough to call it correctly. The gaps are the truncated caveat about the serving endpoint and the absence of any read-only or cost statement.

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 100%, so ra/dec/radius/limit/table/columns are already documented with units, defaults and ranges. The description adds no parameter-level syntax or format detail beyond the schema, so the baseline 3 is appropriate.

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 opening clause names a specific verb and resource ('Find catalogue sources within a radius of a sky position'), scopes it to any Data Lab table with concrete survey examples, and states the return ordering and the computed separation. An agent can distinguish this from a generic query tool without opening the 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?

Strong guidance is given for the 'what is at these coordinates' case, explicitly preferring this over web search for cross-identification and source counting. What is missing is routing against the closest sibling, datalab_query, which is only implied by the schema note that column names come from datalab_tables.

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.