agentsvc-mcp

text_embed

Generate sentence embeddings for semantic search, clustering, and deduplication, or rerank documents by cosine similarity to a query. Runs locally; texts are not stored.

Instructions

Text Embeddings and Rerank — Sentence embeddings (all-MiniLM-L6-v2, 384 dimensions, L2-normalized, multilingual input works best in English) for semantic search, clustering and deduplication, or rerank mode: pass query + documents to get documents sorted by cosine similarity. Runs locally, texts are not stored. Params: texts (1 to 32 strings, max 2000 chars each) for embed mode, or query + documents (up to 64) and top_k for rerank mode. Cost: $0.002 USDC per call. Latency p99: 2000ms.

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": "text_embed"
  }
}

Input Schema

Name	Required	Description	Default
`query`	No
`texts`	No
`top_k`	No
`documents`	No
`include_embeddings`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 21, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and delivers: local execution, no text storage, exact cost ($0.002 USDC/call), and p99 latency (2000ms). These operational traits are exactly the kind of context annotations would otherwise supply, so this is unusually strong disclosure.

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?

Information is front-loaded with the core capability first, then model details, then params, then cost/latency. It is a dense single block with em-dash clauses rather than cleanly separated sentences, but virtually every clause carries useful information.

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 tool with 0% schema coverage, no annotations, and no output schema, the description is nearly self-sufficient: it covers mode selection, limits, cost, latency, and privacy. Gaps remain — 'include_embeddings' is unaddressed and the embed-mode return (the 384-dim vector output) is only implied rather than stated.

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 0%, so the description must compensate, and it does for four of five params: it explains 'texts' (1–32, max 2000 chars — the char limit exceeds the schema, which only sets maxItems), 'query'/'documents' (up to 64), and 'top_k'. It never mentions 'include_embeddings', leaving that parameter undocumented in both schema and description.

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 opens with a specific verb+resource ('Text Embeddings and Rerank') and immediately states the underlying model, dimensionality, and normalization. It distinguishes the two operational modes (embed vs rerank) clearly enough that an agent understands exactly what the tool produces.

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?

It gives concrete use cases (semantic search, clustering, deduplication) and conditionally routes the agent: embed mode with 'texts', rerank mode with 'query + documents' to sort by cosine similarity. It lacks explicit when-not-to-use guidance or sibling comparisons, but the mode-selection context is clear.

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

Deploy Server