Open a LIVE mid-run session so Snapback can watch your run step-by-step and warn you in real time (loop / token / cost / context) - the always-on guardian mode. Returns a session_id. Free, no token. Call session_step as you run, session_end when done.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | No | optional label for your agent/run |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "description": "A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.",
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds real value beyond annotations by disclosing that it returns a session_id, that it is free (no token), and that this is 'always-on guardian mode' with real-time warnings. Annotations cover readOnly/destructive/idempotent hints, but the description goes further with cost and return-value context. Could say more about session lifetime or limits, hence not 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?
Front-loaded with the core action, then the value proposition, then the return value, then the companion-tool workflow. Every clause earns its place; no filler.
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 session-lifecycle entry point, the description covers purpose, return value, cost, and sibling coordination. Output schema exists so return format needn't be fully explained. Minor gaps: no mention of session lifetime, concurrency, or failure modes.
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?
Only one optional parameter (agent_id) and schema description coverage is 100%, so the schema already carries the semantics. The description adds no param-specific detail. Baseline 3 applies.
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?
States a specific verb+resource ('Open a LIVE mid-run session') and immediately explains what the session does: real-time step-by-step watching and warnings for loop/token/cost/context. Clearly distinguishable from siblings like session_step and session_end, whose roles are also named.
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 tells the agent the full workflow: call session_start to open, session_step as you run, and session_end when done. This is a complete lifecycle guide that routes usage across three sibling tools without ambiguity.
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.