Send a message to the feedbk survey-builder agent. It can create, edit, preview, publish, close, and analyze AI-moderated surveys. Omit session_id on the first call; pass the session_id from the previous response on follow-up calls to continue the conversation (sessions expire after an hour of inactivity).
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | ||
| session_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description carries the full burden. It discloses the conversational nature, the agent's ability to perform mutating actions (publish, close), and session expiry. Missing response format and error behavior keeps it from a 5.
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?
Two sentences front-load purpose and include essential session-handling rules without any fluff. Every sentence serves a purpose, making it concise and well-structured.
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?
Given the tool's simplicity (2 params, no output schema), the description covers the operation and the key workflow (session management). It doesn't specify the response structure beyond implying session_id, but that is adequate for this complexity.
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 schema has 0% description coverage, so the description must compensate. It clarifies 'message' as the content to send and thoroughly explains 'session_id' semantics. While message format isn't elaborated, the session guidance adds substantial meaning beyond the bare schema.
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 that the tool sends a message to a survey-builder agent and enumerates its capabilities (create, edit, preview, publish, close, analyze). This offers a specific verb+resource with no ambiguity, and since there are no siblings, it inherently distinguishes itself.
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?
Explicitly instructs when to omit session_id on the first call and when to pass it on follow-ups, providing clear when/when-not guidance. It also warns about session expiration, ensuring the agent knows the operational constraints.
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.
With only one tool, there is no ambiguity or overlapping purposes. The tool's purpose is clearly defined as a conversational interface to survey builder agent, making it impossible to misselect.
The single tool name 'survey_builder' is descriptive and follows a clear snake_case convention. There are no other tools to conflict with, so naming is consistent.
Having a single tool is borderline for the scope of the server. While the tool is designed as an agent that handles multiple survey operations, the tool surface feels thin compared to a typical dedicated survey management system.
The tool description claims to cover create, edit, preview, publish, close, and analyze, covering the core survey lifecycle. However, it omits explicit mention of delete, list, or other administrative operations, leaving minor gaps.
