Skip to main content
Glama

chat

Send prompts to local Ollama models and return replies, with optional system prompts, named conversation context, structured JSON output, and temperature control for extraction tasks.

Instructions

Send a prompt to the local model and return its reply.

Args: prompt: The user message. system: Optional system prompt. With conversation, only applied when the conversation starts. conversation: Optional name; prior turns under this name are sent as context and this turn is appended. Kept in memory for the life of this MCP server process. model: Ollama model name (default from OLLAMA_MODEL). format: "json", or a JSON schema object, to force structured output. think: Enable the model's thinking mode (slower; off by default). temperature: Sampling temperature; use 0 for extraction tasks.

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": "chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
thinkNo
formatNo
promptYes
systemNo
temperatureNo
conversationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that conversation state lives only in process memory, that `system` is applied only on the first turn of a conversation, that thinking mode is slower and off by default, and that `format` can force structured output. Gaps remain around failure behavior (unknown model, schema rejection) and the concrete return shape.

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?

A single front-loaded sentence states the action, followed by a scannable per-parameter list with no filler. The docstring-style Args formatting is functional rather than elegant, but every line earns its place for a seven-parameter tool.

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 seven-parameter tool with no annotations and no output schema, the definition covers input semantics and the key stateful behavior. It falls short of fully complete only because the returned reply's form (plain string vs. structured payload) and error cases are not described.

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 description coverage is 0%, so the Args block is doing all the work, and it documents all seven parameters with meaning beyond the schema — env-derived model default, conditional system-prompt application, conversation context accumulation, json-or-schema for `format`, and temperature 0 for extraction. Only `format`'s accepted values and `think`'s interaction with output are left slightly thin.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a concrete verb and resource: send a prompt to the local model and return its reply. That clearly separates it from `models` (listing) and `forget_conversation` (clearing), but the description never names those siblings, so the differentiation is only inferable.

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?

Usage is only implied: the `conversation` parameter explains that turns accumulate in memory, which hints at when to pass a conversation name, but there is no explicit when-to-use/when-not guidance. It never says to use `forget_conversation` to reset state or when to prefer a stateless call.

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

Deploy Server

Other Tools