Skip to main content
Glama
Sign In

1gateway

by io.github.code0xff
OverviewDiscussionsAdmin

Text embeddings: multilingual BGE-M3 1024-dim vectors for up to 32 texts per call

ai_embed

Use when an agent needs vectors for search, RAG, clustering or dedup. Input: text (GET) or POST JSON {texts:[...]} with up to 32 strings of max 2000 chars each. Output: model, dims (1024), embeddings with index and vector; compare with cosine similarity. Multilingual (100+ languages, strong Korean). Not stored. Example: ?text=x402%20pay-per-call%20API Price: $0.003 USDC (Base or Solana) via x402.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ai_embed"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoOne text to embed (1-2000 chars). For several, POST {"texts":[...]} (up to 32)
textsNoJSON array of up to 32 strings (alternative to text; POST JSON preferred)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

No annotations provided, so the description carries full burden. It discloses input methods (GET vs POST), limits (32 strings, 2000 chars each), output structure (model, dims, embeddings with index/vector), storage behavior ('Not stored'), multilingual support, and pricing ($0.003 USDC via x402). This is rich behavioral context beyond the schema.

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?

Front-loaded with the use case, then input/output details, then storage note, example, and price. Every sentence contributes, but the density is high and the example could be trimmed without losing clarity. Still well-structured and free of fluff.

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?

Given no annotations and no output schema, the description covers everything an agent needs: purpose, input formats, limits, output shape, storage behavior, and pricing. It is complete for a stateless embedding tool.

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. The description adds meaningful context: 'text (GET) or POST JSON {texts:[...]}' clarifies HTTP method differences, and the example shows URL encoding. It also reinforces the batch limit and character cap, though the schema already documents these.

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+resource: generate text embeddings. Names concrete use cases (search, RAG, clustering, dedup) that distinguish it from sibling tools like ai_translate or ai_prompt_injection. An agent can immediately identify the tool's function.

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?

Explicitly says 'Use when an agent needs vectors for search, RAG, clustering or dedup' – clear when-to-use. No when-not-to-use guidance or named alternatives, but no direct embedding sibling exists, so the context is sufficient.

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

All 1gateway 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