Skip to main content
Glama
smallest-inc

Smallest MCP Server

Official
by smallest-inc

chat_with_agent

Run scripted text conversations with a published AI agent to test and refine its prompt. Each message waits for the agent's full turn, supporting tool-using flows.

Instructions

Hold a TEXT conversation with a published agent over the realtime chat WebSocket (mode=chat) — no audio, no phone, just text in / text out. Sends each message in messages in order, waiting for each agent turn to FULLY settle before sending the next — a turn can be several messages (a filler while a tool runs, then the answer), so tool-using flows (auth, lookups) complete instead of being cut off. Returns the full transcript. Use this to test an agent's prompt/behaviour programmatically (e.g. an automated build → test → evaluate → refine loop): run a scripted conversation, read the transcript, then adjust the prompt with update_agent_prompt and run again. This places a real (chargeable) chat session on the agent. Note: the agent must be published; for unpublished drafts use test_draft (mode=chat) to start one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agent_idYesThe agent ID to chat with (must be a published agent)
messagesYesUser turns to send, in order. Each is sent only after the previous turn's reply arrives. For realistic tests, write messages a real caller would send.
settle_msNoSilence after a SUBSTANTIVE agent message before the turn counts as finished. Fillers (messages ending in '…', spoken while a tool runs) are waited on much longer automatically, so this can stay small; raise it only if the agent sends its answer in several slow bursts.
variablesNoPer-call values for {{key}} placeholders in the agent prompt
greeting_wait_msNoTime to wait after connecting for the agent's opening message (0 if it waits for the user first)
reply_timeout_msNoHard cap on how long to wait for a single agent turn before giving up on it
Behavior5/5

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

With no annotations, the description fully discloses behavior: sends messages in order, waits for each turn to fully settle including fillers and tool-using flows, returns full transcript. Also notes constraints: agent must be published.

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?

Description is thorough and well-structured, front-loading key purpose and usage. Slightly long but every sentence earns its place without redundancy.

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 complexity (6 parameters, nested objects, no output schema), description covers all necessary aspects: procedural flow, parameter details, return value (transcript). No gaps for agent to misinterpret.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds significant meaning beyond schema, explaining each parameter's role and nuances (e.g., settle_ms handling fillers automatically, greeting_wait_ms for agent opening message). Context helps agent choose correct values.

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 clearly states the tool holds a TEXT conversation with a published agent over WebSocket, specifying mode=chat and distinguishing from audio/phone calls. It differentiates from sibling tool 'test_draft' for unpublished agents.

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?

Explicitly describes when to use (testing agent programmatically, automated build-test loop) and when not to (for unpublished drafts, use test_draft). Also mentions it's chargeable and requires the agent to be published.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/smallest-inc/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server