evaluate_on_call_frame

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

Discloses the paused state requirement but does not mention potential side effects of evaluating arbitrary expressions, authorization needs, or error behavior. With no annotations, description carries the full burden; it covers essential behavioral constraints but leaves gaps.

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 concise sentences: first states purpose and context, second provides prerequisite. No filler, front-loaded with key information.

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 has 4 parameters and no output schema, the description covers prerequisite and purpose but lacks details on return value, error handling, or behavior when not paused. Adequate but not fully complete for a debugging tool that returns evaluation results.

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 schema already provides descriptions for all parameters. The description adds a hint that callFrameId comes from get_paused_state, which aligns with schema but does not significantly enhance parameter understanding beyond what the schema offers.

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?

Clearly states the tool evaluates an expression in the context of a paused call frame, specifically to access local variables. Distinguishes from other evaluate tools by specifying the paused call frame context.

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?

Explicitly states the prerequisite: target must be paused and callFrameId comes from get_paused_state. Provides clear guidance on when to use, but does not explicitly exclude other scenarios or compare with siblings like evaluate_in_main.

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