Change active trading skill overlay for this user. Immediately affects all subsequent get_signals calls and downstream channels.
| Name | Required | Description | Default |
|---|---|---|---|
| skill_id | Yes | trading_skills.id (e.g. 'aggressive_v0'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full burden. It discloses that the change is immediate and affects subsequent calls, but does not specify reversibility, error behavior, or whether other tools are also affected.
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, no wasted words. Front-loaded with the action and provides a clear effect statement.
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 simple mutation with one parameter and no output schema, the description sufficiently explains what the tool does and its impact. Missing details about error cases or default behavior but overall adequate.
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 100% and the description adds no extra detail beyond what the schema provides for the single parameter skill_id. Baseline score 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?
The description clearly states the verb 'Change' and the resource 'active trading skill overlay'. It distinguishes from sibling tools which are primarily getters and validators, making this the only tool for setting overlays.
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 mentions that changes immediately affect get_signals calls and downstream channels, implying when to use. However, it does not specify prerequisites (e.g., authentication), when not to use, or alternatives from siblings.
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.
Each tool targets a distinct purpose: state readings (raw vs. view vs. AI-synthesized), signals vs. historical triggers, execution (place/close/update stops), pre-trade validation, and skill management. Cross-references between tools (e.g., get_signals vs. get_trigger_history) explicitly clarify boundaries, leaving no ambiguity about which tool to call.
All tools follow a consistent verb_noun pattern with the 'decker.' prefix: get_* for reads, place/close/update for actions, set_* for settings, and validate_* for checks. This uniformity makes the tool surface predictable and easy to navigate.
14 tools is well-scoped for a comprehensive trading engine MCP, covering state observation, signal generation, execution, risk management, and user configuration. Each tool earns its place and there are no redundant or missing core functions.
The tool surface covers the full trading lifecycle: reading market state (multiple layers), obtaining signals and historical triggers, checking positions, opening/closing positions, updating protective stops, validating intent before orders, and managing skill overlays. The absence of a cancel_order tool is explicitly justified (only market orders), and the domain shows no obvious gaps.