Get a validated next-action proposal for Slay the Spire 2 Ironclad: KEV handles tactical choices, Luna handles strategy, deterministic logic handles forced or unique actions.
Create one validated proposal: KEV for tactical choices, Luna for strategy, deterministic for forced or unique actions.
| Name | Required | Description | Default |
|---|---|---|---|
| route_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing side effects, validation behavior, and persistence. 'Validated' hints at some checking logic, but the description does not say whether this creates state, requires authorization, or is safe to call repeatedly.
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 efficiently conveys the core action and mode-selection rules. It loses points only because the introduced terms KEV and Luna are unexplained, making the compactness cryptic rather than purely helpful.
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?
While an output schema exists, the definition still fails to explain the only parameter, the meaning of the strategy codes, or the validation semantics. For a non-trivial recommendation tool with no annotations, this leaves critical invocation details missing.
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 one parameter, route_id, with 0% schema description coverage, so the description must compensate. It never mentions route_id, its nullability, or how it influences the proposal, leaving the agent unable to determine correct parameter usage.
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 names a specific deliverable ('one validated proposal') and contrasts with execution-oriented siblings like execute_proposal. The strategy qualifiers (KEV, Luna, deterministic) imply distinct proposal-generation modes, though the cryptic domain terms prevent full clarity.
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 gives internal selection guidance ('KEV for tactical choices, Luna for strategy, deterministic for forced or unique actions') but never states when to use this tool versus siblings such as get_legal_actions, plan_map_route, or execute_proposal. No exclusions or prerequisites are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.