session_evaluate

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states that it executes JavaScript and returns a result, but fails to mention that code execution can be destructive, may cause navigation, could throw errors, or that the result format is unspecified. This is a significant gap for a powerful tool with no annotation guardrails.

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 a single, focused sentence that front-loads the core action and result. There is no filler or redundancy. While it is underspecified in other dimensions, conciseness itself is optimal for a tool of this simplicity.

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 complexity of code execution, the description is incomplete. It lacks any statement about return value format, error handling, side effects, or whether tabId is required to select a non-active tab. Without an output schema or annotations, an agent cannot predict what the tool will actually return or how to handle failures, making it insufficient for reliable invocation.

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 schema provides no descriptions and coverage is 0%, so the description must compensate. It clarifies that 'code' is JavaScript to be executed, but does not explain 'tabId' at all — whether it targets a specific tab or defaults to the active one. The description adds minimal value beyond the bare schema, leaving the agent guessing about tabId semantics.

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 executes JavaScript in the page context and returns the result. The verb 'execute' and resource 'JavaScript' are specific, and it is distinct from sibling tools like session_snapshot or session_read_page that read state instead of running arbitrary code. Even without explicit sibling differentiation, the purpose is unambiguous.

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 offers no guidance on when to use this tool over alternatives. It does not mention that this is for arbitrary script execution, nor does it indicate when not to use it (e.g., preferring dedicated navigation or click tools). The absence of any contextual cue leaves the agent to infer applicability solely from the schema's existence.

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