Skip to main content
Glama
Sign In

Scoopkit

by dev.scoopkit
OverviewDiscussionsAdmin

Search AI news events

search
Read-only

Semantic search over events (Pro+)

Natural-language query embedded and ranked by cosine similarity against published events — not a keyword/text match. Each result is a normal event object plus relevance_score (0-1). Requires Pro tier or above; free-tier keys get 403 with an upgrade_url.

Responses:

200: Successful Response (Success Response) Content-Type: application/json

Example Response:

{
  "data": [
    {
      "event_id": "Event Id",
      "schema_version": "Schema Version",
      "taxonomy_version": "Taxonomy Version",
      "primary_category": "Primary Category",
      "subcategory": "Subcategory",
      "categories": [
        "string"
      ],
      "type_confidence": 1.0,
      "headline": "Headline",
      "summary": "Summary",
      "reported_at": "2023-01-01T00:00:00Z",
      "orgs": [
        "string"
      ],
      "models": [
        "string"
      ],
      "source_url": "Source Url",
      "article_count": 1,
      "relevance_score": 1.0
    }
  ],
  "pagination": {
    "has_more": true,
    "count": 1
  },
  "meta": {
    "request_id": "Request Id",
    "taxonomy_version": "Taxonomy Version",
    "tier": "ApiTier"
  }
}

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": {
      "q": "<q>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesNatural-language search query
limitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint=false. The description adds material behavioral facts the annotations don't carry: the ranking mechanism (cosine similarity), the extra relevance_score field per result, the Pro+ authorization gate, and the exact failure mode for free-tier keys (403 with an upgrade_url). That is precisely the kind of beyond-schema context this field should reward.

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?

The prose is tight and front-loaded: purpose, mechanism, result shape, and auth gate all land in two sentences. The appended example response is long and contains low-value placeholders ('Event Id', 'Schema Version'), but given there is no output schema it does convey the real return envelope. Slight bloat, no wasted prose.

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 carries the burden of explaining returns, and it does: event objects plus relevance_score, an array under data, a pagination block with has_more, and a meta object. Combined with the tier-gating detail, an agent can call and interpret this correctly. The only gap is limit/pagination request-side semantics.

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 coverage is 50%: q is documented but limit is only constrained (1-100, default 20) without explanation. The description enriches q's meaning ('natural-language query embedded and ranked by cosine similarity'), but never addresses limit or how it interacts with the pagination.has_more field shown in the response. With half the parameters undocumented in schema, the description only partially compensates.

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 (semantic search) and resource (events) and immediately distinguishes itself from keyword matching: 'Natural-language query embedded and ranked by cosine similarity against published events — not a keyword/text match.' That contrast lets an agent tell it apart from list_events or get_event without opening their schemas.

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 clarifies the mode of search but never names an alternative tool or a condition under which the agent should prefer list_events or get_event instead. The tier requirement ('Pro tier or above') is useful context but is a prerequisite, not usage guidance. The when-to-use signal is implied by 'semantic' rather than stated.

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

All Scoopkit 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