next_actionReturns one bounded next action for a valve and lifecycle stage without performing registration, submission, messaging, or any external write.
| Name | Required | Description | Default |
|---|---|---|---|
| stage | Yes | ||
| valve | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable context by explicitly listing excluded operations (registration, submission, messaging, external writes) and clarifying the output is a single 'bounded' action, which goes beyond the annotation safety profile.
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, front-loaded sentence that conveys the core purpose and key constraints without extraneous wording. Every phrase earns its place.
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 no output schema, the description should describe the return value more concretely. It says 'one bounded next action' but doesn't explain what a next action looks like or how it relates to the enums. Still, the read-only nature and core behavior are clear, so it's minimally viable.
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?
Schema coverage is 0%, so the description must compensate, but it only echoes the parameter names ('valve and lifecycle stage') without explaining the meaning of the enums or how parameters interact. This adds little beyond the schema and leaves the agent without enough semantic detail.
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 it 'Returns one bounded next action' for a valve and lifecycle stage, specifying the verb, resource, and scope. This distinguishes it from sibling tools like route_valve or route_reputation_skill, which imply different operations.
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 mentions that it does not perform registration, submission, messaging, or external writes, which implies use for read-only planning. However, it provides no explicit guidance on when to prefer this tool over alternatives, nor any exclusion conditions referencing sibling tools.
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.
Most tools have clearly distinct purposes, such as status, learning, market listing, retention, and routing. However, route_valve also returns a next action, which overlaps with the dedicated next_action tool, causing slight ambiguity.
Naming conventions are mixed: some tools start with a verb (learn_reputation, list_generation_market, route_reputation_skill, route_valve), while others are noun phrases (gateway_status, next_action, retention_plan). This lack of a consistent pattern makes it harder to predict tool names.
With 7 tools, the server is well-scoped for a reputation gateway that provides status, learning, market, routing, and retention insights. Each tool earns its place, and the count is within the ideal range.
The server covers key advisory functions like status, curriculum, market, next actions, retention, and routing, but is entirely read-only and lacks any tool to list available valves or execute actions. This leaves notable gaps for agents that need to actually interact with the reputation system.