start-builder-chatStart a new builder chat via POST /v1/new-chat and sync bot_flow with the active agent version.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes | JSON or plain text body returned by the Botsify HTTP API |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral detail beyond the annotations by mentioning the POST endpoint and the syncing of bot_flow with the active agent version. The annotations already indicate non-read-only (readOnlyHint=false) and non-idempotent (idempotentHint=false), which aligns with the described mutation. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that front-loads the primary action and includes the essential behavioral detail. There is no unnecessary information or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no parameters and an existing output schema, the description is complete. It explains what the tool does and key side effects (syncing bot_flow). The presence of sibling tools and annotations provides additional context without requiring more from the description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema coverage is trivially 100% and there is no parameter info to add. The description does not need to explain any inputs, and the baseline for 0-parameter tools is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Start a new builder chat'), the resource (builder chat), and includes the specific endpoint (POST /v1/new-chat) plus the syncing behavior. This distinguishes it from other builder-related tools like stream-builder or store-builder-response.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The context of when to use the tool is clear: to start a new builder chat. It does not explicitly mention alternatives or when not to use it, but the description's clarity provides sufficient usage context for a tool with no parameters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools have overlapping purposes, such as send-converse-message, send-inbox-message, send-user-message, and stream-user-message, which all deliver messages but with subtle differences. Similarly, list-bot-messenger-users and list-messenger-users both fetch messenger users, and start-builder-chat, clear-builder-conversation, and store-builder-response all manage builder chat state. Descriptions help, but the boundaries are still confusing.
Tool names consistently use hyphenated lowercase verb-noun format, but the verbs and nouns vary significantly in specificity. For example, 'get-query-response' vs 'query-mcp-agent' vs 'stream-user-message' all imply querying but with different styles. The pattern is readable but not highly predictable, with some names like 'change-user-activation' and 'patch-instruction-section' deviating from the simple verb_object structure.
With 44 tools, this server feels overloaded. The breadth covers bots, messaging, templates, whitelabel, and versions, but many tools could be consolidated (e.g., multiple message-sending variants). The count exceeds the 25-tool threshold for 'too many', making it difficult for agents to select the right tool without extensive context.
The tool set covers the main lifecycle: agent creation, versioning, deployment, deletion, messaging, conversation history, user management, template management, and whitelabel operations. Minor gaps exist, such as missing delete for WhatsApp templates or update operations for user attributes, but these are workable edge cases. Core workflows are well supported.