RuntimeEval

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

The description discloses key behavioral requirements: use of a return statement, access to all notebook variables, and persistence behavior when a name is provided. With no annotations present, the description carries the burden, but it does not mention potential side effects of executing arbitrary code, error behavior, or async resolution. It adds useful context but is not fully transparent.

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 concise and front-loaded: it states the operation, then the critical return rule and usage preference, then illustrative examples. Every sentence adds useful information without repetition or filler.

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 tool's moderate complexity, the description adequately covers the essential usage context: what it evaluates, the return requirement, the runtime scope, and the persistence option. It could go further by explaining error or timeout behavior, but the schema already documents timeout and the return value is dynamic, so the absence of an output schema is not a major gap.

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%, so the baseline is 3. The description adds value beyond the schema by providing concrete examples of expressions, emphasizing the return requirement, and clarifying that the evaluation context includes all notebook variables. This extra guidance helps an agent construct a correct body parameter.

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 a specific action ('Evaluate an expression') and a specific resource ('in the Observable runtime context') with access to notebook variables. It also differentiates itself from the similar Eval tool by positioning itself as the preferred choice for derived values from runtime state.

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 explicitly says 'Prefer this over Eval when computing derived values from runtime state,' giving clear context for when to use it. However, it does not mention when not to use it or how it compares to BrowserEval, another sibling tool, so it lacks a full set of exclusions.

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