evaluate

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions the paused requirement, omitting crucial details such as potential side effects of arbitrary JavaScript execution, error behavior, or what happens if not paused. This is insufficient for a code-execution tool.

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 two sentences, front-loaded with the core action and the critical paused constraint. Every word earns its place, with no redundancy or unnecessary detail.

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?

The tool has three parameters, no output schema, and no annotations. The description is minimal and leaves gaps around return format, the role of connection_id, and how it differs from sibling evaluation tools like renderer_evaluate and v8_evaluate. This is incomplete for an agent to select and invoke the tool correctly in context.

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 input schema provides 100% coverage with descriptions for all three parameters (expression, call_frame_id, connection_id), so the schema already carries the parameter documentation. The description adds no extra semantic value beyond referencing 'specific call frame,' which is already captured in the call_frame_id parameter description. Baseline 3 is appropriate.

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 evaluates JavaScript in a call frame, using a specific verb and resource. It also notes the paused requirement, which adds specificity. However, it does not explicitly differentiate from sibling tools like renderer_evaluate or v8_evaluate, so it misses the top 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 a key usage condition ('Only works when paused') but offers no guidance on when to select this tool over alternatives such as renderer_evaluate or v8_evaluate. The usage context is implied through the call frame and paused requirement, but explicit exclusions or alternative recommendations are absent.

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