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

Annotations provide no behavioral hints, so the description carries the full burden. It discloses persistence, navigation side effects, and exception reporting. Does not explicitly warn about destructive potential, but execution context is clearly described.

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?

Three sentences with zero redundancy. Front-loads the main purpose, then adds behavioral caveats and exception handling. Every sentence earns its place.

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 powerful arbitrary-execution tool with no output schema and minimal annotations, the description covers persistence, navigation, and error reporting. It lacks mention of return value format or potential async behavior, but these are minor for the intended use case.

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 baseline is 3. The description adds context about how the 'script' parameter behaves (runs in current page, persists) beyond the bare schema description, though it does not detail return value or formatting specifics.

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 it executes JavaScript in a live session and returns the result, with a specific verb and resource. Explicitly contrasts with the sibling 'eval' tool, making differentiation immediate.

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?

Directly names the alternative stateless eval tool and explains the key difference: persistence vs. throwaway page. This gives agents a clear decision rule for when to use session_eval over eval.

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