Skip to main content
Glama
Sign In

Agent Tools API

by app.openkrill
OverviewDiscussionsAdmin

Search open data by kind

data_search
Read-onlyIdempotent

Search every licence-clean source of one kind at once (jobs, papers and books as work, posts, apps, media, entities, metrics) and get de-duplicated rows. Costs 1 credit per source searched, at most 8. Every row has name (platform/collection/id), kind, its fields and source {platform, url, license, attribution, fetched_at, terms_url}; quote source.attribution when you show a row.

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": {
      "kind": "<kind>",
      "q": "<q>"
    },
    "name": "data_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesThe words to search for.
kindYes
page_sizeNoRows per page, 1 to 50 (default 10).
platformsNoOptional: only these platforms, such as ["arxiv", "openalex"].

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world behavior, so the description's real contribution is the billing model (1 credit per source, capped at 8), the de-duplication guarantee, and the per-row licence/attribution contract. That is useful context beyond the annotations, though it says nothing about pagination limits or result ordering.

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?

Two sentences, front-loaded with the core operation, then cost and row-shape details. Dense but every clause carries information; the attribution instruction is a bit of an appendage but still actionable.

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 no output schema, the description does well to describe the row shape (name, kind, fields, source with url/licence/attribution) and the credit cap. Gaps remain around pagination behavior, ordering, and how many sources the max-8 cap covers relative to the platforms filter.

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 75%, so the schema already documents q, page_size and platforms. The description adds meaning the schema lacks, notably mapping 'papers and books' to the 'work' kind and clarifying that the search fans out across multiple sources at once. It says nothing extra about platforms or page_size.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: search all licence-clean sources of a single kind at once and return de-duplicated rows. The enumerated kinds make the scope unambiguous. It doesn't explicitly contrast with siblings like data_get or data_list, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (query all sources of one kind in a single call) and adds a cost rule of 1 credit per source, at most 8, which informs call decisions. However, it never says when to prefer a sibling such as data_get or data_list, nor when not to use this tool.

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

All Agent Tools API toolsInspect
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