query-mcp-agentSend an agentic query via POST /v1/mcp-agent/query authenticated with the X-Api-Key header and fbId.
| Name | Required | Description | Default |
|---|---|---|---|
| fbId | Yes | End-user fbId used to load or create the messenger user | |
| query | Yes | User question for the agent |
| 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?
Annotations already convey that the tool is non-idempotent, open-world, and non-destructive. The description adds the POST endpoint, X-Api-Key header, and fbId requirement, which is useful context beyond annotations, but it does not elaborate on side effects, rate limits, or other behavioral nuances.
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 concise sentence, front-loaded with the action and resource, and includes only essential information. There is no unnecessary wording 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?
With 2 well-documented parameters and an output schema present, the description plus annotations cover the essential invocation details (endpoint, authentication). It lacks usage scenario guidance, but for a simple query tool, this is sufficiently complete.
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 input schema fully documents both parameters with clear descriptions. The description itself only mentions fbId and 'agentic query' without adding any new semantic detail beyond what the schema already provides, so the baseline of 3 is appropriate.
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 uses a specific verb ('Send') and resource ('agentic query') and includes the exact endpoint and authentication method, clearly distinguishing it from sibling CRUD operations. This makes the tool's purpose unambiguous.
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 description does not explicitly state when to use this tool versus alternatives, nor does it mention any exclusions. It implies usage by describing the operation itself, but lacks direct guidance on scenario selection.
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.