QuantConnect

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

The description adds some behavioral context beyond annotations: it mentions the snapshot updates every 10 minutes, which helps set expectations about data freshness. However, annotations only provide a title ('Read live insights'), so the description carries most of the burden. It doesn't disclose other important traits like authentication needs, rate limits, or what 'insights' specifically include. No contradiction with annotations exists.

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 extremely concise and front-loaded, with only two sentences that directly address the tool's function and a key behavioral trait. There is no wasted text, and every sentence adds value, making it easy to parse quickly.

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 that there is an output schema (per context signals), the description doesn't need to explain return values. However, with 0% schema description coverage and no parameter details in the description, it leaves significant gaps in understanding how to invoke the tool. The description covers the basic purpose and update frequency but misses critical details about parameters and usage context, making it only minimally 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?

The description provides no information about parameters, while the schema description coverage is 0% (based on context signals). This leaves all parameters undocumented in both the schema and description. The description doesn't compensate for this gap by explaining what 'model', 'start', 'end', or 'projectId' mean in context, making it hard for an agent to use the tool correctly.

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 tool's purpose: 'Read out the insights of a live algorithm.' This specifies the verb ('read out') and resource ('insights of a live algorithm'), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from sibling tools like 'read_backtest_insights' or 'read_live_logs', which prevents a perfect score.

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 minimal usage guidance. It mentions that 'The snapshot updates about every 10 minutes,' which gives some context about data freshness, but it doesn't explain when to use this tool versus alternatives like 'read_backtest_insights' or other live data tools. No explicit when/when-not instructions 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.