vars

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

With no annotations provided, the description carries the full burden. It mentions that actions include clear_all, implying it can clear all globals. However, it doesn't disclose side effects like persistence, whether changes are permanent, or if there are any side effects on the running kernel. The description says 'change' but doesn't elaborate on mutability beyond that.

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 compact and front-loaded with the main purpose. The action list is useful and not verbose. It is structured as a single sentence, which is efficient, but could be slightly clearer with the parameter behavior.

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 complexity (5 parameters, 5 actions) and the lack of schema parameter descriptions, the description is incomplete. It doesn't explain the 'pattern' parameter or 'include_system' flag, which an agent might need to call correctly. However, an output schema exists, which may provide some guidance on return values, but not on parameter semantics.

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 description coverage is 0%, meaning the schema provides no descriptions for parameters. The description lists actions but doesn't explain what each parameter does. For example, 'pattern' is a parameter but not mentioned in the description, and its purpose is unclear. The description only hints at 'name' and 'value' but leaves out 'pattern' and 'include_system'. This is a significant gap.

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: to inspect or change kernel globals, listing specific actions. It is distinct from siblings like 'kernel' or 'status' by focusing on variable manipulation. However, it could be more specific about the resource (kernel's global symbols) being unique, as 'inspect or change' is a bit broad.

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 explicit use cases: 'use this to see what a notebook replay actually defined, or to clear one symbol without restarting.' This explains when to use it, but doesn't explicitly mention when not to use it or compare with alternatives. However, given the simple nature, it's adequate.

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