Skip to main content
Glama
Platano78

Smart-AI-Bridge

manage_conversation

Start, continue, resume, or search conversation threads across sessions. Retrieve history and analytics to track multi-turn interactions.

Instructions

Manage long-running conversation threads across sessions. The conversation state machine: call start (topic is recommended but not required — used for search/grouping) to receive a thread_id + continuation_id; pass continuation_id on each follow-up turn with continue to extend the thread; use resume with a stored thread_id to pick up an old thread from any session. history returns the messages in one thread; search queries across all stored conversations by free-text query; analytics reports per-thread/per-user usage stats. Each action requires only the parameters listed in its description below — extra fields are ignored. Persists conversation state to the configured threading store (non-destructive to user files; the threading store grows over time). Returns: {success, action, data} where data shape varies — start: {thread_id, continuation_id, topic, created_at}. continue: {thread_id, continuation_id, response, message_count}. resume: {thread_id, topic, last_message_at, message_count}. history: {thread_id, messages:[{role, content, timestamp}]} (capped at limit, default 10). search: {query, matches:[{thread_id, topic, snippet, score}]}. analytics: {total_threads, threads_by_user, avg_messages_per_thread, recent_topics}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: start (new thread), continue (with continuation_id), resume (with thread_id), history (get thread history), search (search conversations), analytics (get analytics)
thread_idNoThread ID to resume or get history (optional)
continuation_idNoContinuation ID from previous response (optional)
topicNoTopic for new conversation (optional)
queryNoSearch query for conversations (optional)
user_idNoUser identifier (optional, defaults to "default")
platformNoPlatform identifier (optional)
limitNoLimit for history results (optional, default 10)
Behavior5/5

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

With no annotations, the description fully discloses behavioral traits: the state machine flow, persistence to a threading store, non-destructive nature to user files, growing store, and exact return shapes for each action.

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?

The description is lengthy but efficiently packed with information; it front-loads the purpose and uses a semicolon-separated list for actions. Slightly verbose but still clear.

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 the tool has 8 parameters, 6 actions, no output schema, and no annotations, the description covers every needed aspect: state machine, parameter usage, return shapes, limits, and persistence behavior.

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 100% so baseline is 3, but the description adds value by integrating parameter usage into action narratives (e.g., 'topic is recommended but not required — used for search/grouping') and clarifying defaults (e.g., user_id defaults to 'default').

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 it manages conversation threads across sessions, lists all six actions with specific verbs (start, continue, resume, history, search, analytics), and differentiates from sibling tools like ask or explore by focusing on conversation state management.

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?

Provides explicit when-to-use guidance for each action (e.g., 'pass continuation_id on each follow-up turn with continue', 'use resume with a stored thread_id to pick up an old thread') and notes that extra fields beyond required parameters are ignored, helping the agent select the correct action.

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/Platano78/Smart-AI-Bridge'

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