Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

Embed text as a vector

embed_text
Read-onlyIdempotent

Converts text into a raw embedding vector using the engine’s configured model, returning the vector, dimensions, and model name for storage or custom comparison. Nothing is stored.

Instructions

Turn a piece of text into an embedding vector with the engine's configured embedding model and return {embedding, dimensions, model}. Use it when you need the raw vector, for example to store it or compare it yourself; to search, use semantic_search for vector collections or query with EMBED() and COSINE_SIMILARITY() for table columns. Nothing is stored.

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": {
      "text": "<text>"
    },
    "name": "embed_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to embed, such as a sentence or short passage.
modelNoAccepted for compatibility; the engine always uses its configured embedding model, reported in the response's `model` field.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.1
    • changedInput schema / properties / model / description
      Previous value: -"Embedding model (default: configured default - minilm)"New value: +"Accepted for compatibility; the engine always uses its configured embedding model, reported in the response's `model` field."
    • changedInput schema / properties / text / description
      Previous value: -"Text to embed"New value: +"Text to embed, such as a sentence or short passage."
  2. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so safety is largely covered. The description still adds value beyond them: the concrete return fields, the explicit "Nothing is stored" side-effect statement, and the note that embedding uses the engine's configured model. It does not discuss size limits, batching, or dimension variability per model, which is the main remaining gap.

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?

Three tight sentences: purpose and return shape first, usage and alternatives second, side-effect clarification last. Every clause carries information and nothing is repeated or padded.

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?

There is no output schema, but the description supplies the return fields inline, so an agent knows what comes back. For a two-parameter read-only tool with full schema coverage, nothing needed to call it correctly is missing.

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 100%, so both `text` and `model` are already documented in the schema, and the description largely restates the configured-model behavior. It reinforces the important quirk that `model` is compatibility-only rather than overriding the engine, but adds no syntax, format, or length guidance beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 description pairs a specific verb and resource ("Turn a piece of text into an embedding vector") with the exact return shape {embedding, dimensions, model}. It also explicitly distinguishes itself from `semantic_search` and `query` with EMBED()/COSINE_SIMILARITY(), so an agent can tell it apart from siblings without opening any schema.

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?

It states the selecting condition ("when you need the raw vector, for example to store it or compare it yourself") and then routes the agent to the correct alternative for each case: `semantic_search` for vector collections and `query` with EMBED() for table columns. Both when-to-use and the competing options are named explicitly.

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