session_eval

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

Annotations only provide a title and no read-only or destructive hints, so the description carries the full burden of behavioral disclosure. 'Execute arbitrary JavaScript' implies potentially significant side effects, but the description does not warn that executing arbitrary code can modify page state, trigger navigation, send network requests, or otherwise alter the session. It also does not explain error behavior or execution context.

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 sentence that is concise, front-loaded with the action, and contains no filler. Every word contributes meaning: 'arbitrary' signals scope, 'in the browser session' gives context, and 'return the result' sets expectations for output.

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?

For a tool that executes arbitrary JavaScript, the description is incomplete. It does not specify how the result is serialized or returned, whether promises or async code are supported, how exceptions are handled, or what security/safety implications exist. The absence of an output schema and meaningful annotations makes this lack of context more significant.

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 already describes both parameters with 100% coverage: 'JavaScript code to execute' and 'Session ID'. The description adds the concepts of 'arbitrary' execution and returning the result, but does not provide parameter-level details beyond the schema. Given full schema coverage, a baseline of 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 uses a specific verb ('execute') and resource ('JavaScript in the browser session') and clearly states the return behavior ('return the result'). It is not a tautology and gives a clear sense of the operation, though it does not explicitly differentiate itself from the sibling tool 'eval', which may also execute JavaScript.

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?

No guidance is provided about when to use this tool versus alternatives. The sibling list includes 'eval', which could plausibly be the more general-purpose JavaScript execution tool, but the description does not explain when session_eval is the right choice, nor does it mention any exclusions or prerequisites beyond the required parameters.

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