next_levelChallenge mode: move to the next level, as the bench's "Next level" button, and only when it would be offered: every test of the current level passed and a next level exists. Returns {level, levels}, the new level (index); session_status's level changes with the bench's next state. No level skipping.
| Name | Required | Description | Default |
|---|---|---|---|
| session | No | ||
| agent_token | No |
Changes observed during successful MCP inspections.
Input schema / properties / agent_token / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / agent_token / defaultAdded value: +nullInput schema / properties / agent_token / typeRemoved value: -"string"Input schema / properties / session / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / session / defaultAdded value: +nullInput schema / properties / session / typeRemoved value: -"string"Input schema / requiredRemoved value: -[
- "session",
- "agent_token"
-]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description discloses that this mutates challenge state, returns {level, levels}, and causes session_status's level to change. It does not describe error behavior when the precondition is not met, but it adds meaningful behavioral context that the annotations do not cover.
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 front-loaded with the action and condition, and every clause carries useful information. The semicolon-heavy phrasing is a bit dense, but there is little wasted text.
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 state-changing challenge action, it explains the trigger condition, return shape, and side effect on session_status. However, with no output schema and no parameter descriptions, it omits how to supply session or agent_token and does not cover failure behavior, leaving notable gaps.
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 two parameters ('session' and 'agent_token') with 0% description coverage, and the description does not mention either parameter. It fails to compensate for the schema gap, leaving an agent with no guidance on how these inputs affect the call.
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 states a specific action ('move to the next level') and ties it to challenge mode and the bench's Next level button. It is clearly distinguishable from siblings in intent, though it does not explicitly name alternative tools.
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?
It gives a precise condition for use: only when every test of the current level passed and a next level exists. It also says 'No level skipping,' which clarifies a negative constraint, but it does not name alternative tools or spell out what to do when the condition is not met.
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.