QuantConnect MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description doesn't contradict the annotations (destructiveHint: false indicates it's non-destructive, which aligns with 'create' operations typically being additive). However, it adds no behavioral context beyond what annotations provide. It doesn't mention whether this starts an asynchronous job, has cost implications (despite 'estimatedCost' in schema), requires specific permissions, or has rate limits. With annotations covering only destructiveness, the description carries significant burden but provides minimal behavioral insight.

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 maximally concise - a single sentence with zero wasted words. It's front-loaded with the core action and doesn't contain any unnecessary elaboration. While this conciseness comes at the expense of completeness, as a standalone text it's efficiently structured.

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?

Given the complexity implied by the rich input schema (11+ nested properties) and the existence of an output schema, the description is severely inadequate. It doesn't explain what domain this operates in (algorithmic trading optimization based on sibling tools), what an optimization job entails, or how it relates to other tools like 'estimate_optimization_time' or 'list_optimizations'. The description fails to provide the contextual framing needed to understand when and how to use this tool effectively.

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?

With 0% schema description coverage (the schema has detailed parameter descriptions but they're in the schema itself, not counted as 'description coverage' for this evaluation), the description 'with the specified parameters' adds almost no semantic value. It doesn't explain what the single 'model' parameter contains, what optimization means in this domain, or how parameters relate to the optimization process. The description fails to compensate for the schema's technical documentation with accessible explanations.

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 'Create an optimization with the specified parameters' is a tautology that essentially restates the tool name 'create_optimization' without adding meaningful specificity. It doesn't explain what an 'optimization' is in this context (e.g., algorithmic trading optimization, parameter tuning) or what resource it creates beyond the generic term. While the title annotation 'Create optimization' provides minimal context, the description itself fails to clarify the purpose beyond the obvious.

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 provides absolutely no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a compiled project first), when optimization is appropriate, or how it differs from related tools like 'create_backtest' or 'update_optimization' in the sibling list. The agent receives no contextual cues about appropriate usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.