Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

Generate text with the engine's LLM

generate_text
Read-only

Generate text from a prompt using the configured SynapCores LLM to summarize or explain outputs from other tools within a multi-step workflow.

Instructions

Generate text from a prompt with the LLM configured on the SynapCores engine and return {text, model, tokens_used, processing_time_ms}. Use it to summarize or explain results from other tools, such as predict or query output, inside a multi-step workflow; to generate per row inside SQL, use GENERATE() in query. It does not read or change your data, and output is sampled, so repeated calls can differ.

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": {
      "prompt": "<prompt>"
    },
    "name": "generate_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoModel name to use instead of the engine's configured completion model.
promptYesThe full prompt text.
max_tokensNoMaximum tokens to generate (default 100); raise it for longer answers.
temperatureNoSampling temperature; lower is more focused (default 0.7).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.0.1
    • changedInput schema / properties / max_tokens / description
      Previous value: -"Max tokens to generate (default: 100)"New value: +"Maximum tokens to generate (default 100); raise it for longer answers."
    • changedInput schema / properties / model / description
      Previous value: -"Optional model override (default: gateway's configured completion model)"New value: +"Model name to use instead of the engine's configured completion model."
    • changedInput schema / properties / prompt / description
      Previous value: -"Prompt text"New value: +"The full prompt text."
    • changedInput schema / properties / temperature / description
      Previous value: -"Sampling temperature (default: 0.7)"New value: +"Sampling temperature; lower is more focused (default 0.7)."
  2. First observedv1.0.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true and idempotentHint=false; the description justifies and explains both by stating 'It does not read or change your data' and that 'output is sampled, so repeated calls can differ.' That non-determinism warning is the exact behavioral context an agent needs before retrying or caching results, and it is not derivable from the hint alone.

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, front-loaded with what the tool does and returns, then usage routing, then behavioral caveats. No filler or restated name/title content.

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?

No output schema exists, but the description enumerates the returned fields itself and flags non-determinism and the no-data-access guarantee. For a four-parameter, single-required-field generation tool, nothing material 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 description coverage is 100%, including defaults (max_tokens 100, temperature 0.7) and guidance about raising max_tokens, so the schema already carries the parameter burden. The description adds no additional parameter guidance such as prompt length limits or model-name format, so it sits at the baseline.

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?

Specific verb+resource ('Generate text from a prompt with the LLM configured on the SynapCores engine') plus an explicit return shape {text, model, tokens_used, processing_time_ms}. It also distinguishes itself from the sibling `query` and from row-wise SQL generation, so an agent can pick it without opening the 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?

Gives a concrete use case ('summarize or explain results from other tools, such as `predict` or `query` output, inside a multi-step workflow') and an explicit alternative for the row-wise case ('to generate per row inside SQL, use GENERATE() in `query`'). Both when-to-use and when-to-use-something-else are stated.

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