run_script

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

Very rich behavioral disclosure: syntax checked before execution, return values with return;, params as JSON input, UI/clipboard/dynamic requests rejected in background mode, explicitly not a sandbox, and timeout replay warning. Adds substantial context well beyond the annotations.

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?

Dense but front-loaded with the core action, then constraints. Some sentences are terse but every one adds a distinct constraint; minor density cost.

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 a complex, destructive, open-ended execution tool with no output schema, the description covers execution contract, input format, restrictions, and safety caveats well. Lacks explicit handling for document_path and timeout_seconds details.

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 0% with 5 params, so the description carries full burden and does well: clarifies script vs script_path exclusivity, params as JSON input, and return; semantics. document_path and timeout_seconds are implied only loosely, but coverage is strong.

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?

States a specific verb+resource: runs ExtendScript in a shared background executor. Distinguishes from batch_cards by pointing to it for long jobs, though it doesn't fully differentiate from other execution siblings like recover_execution.

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?

Clear guidance: supply either script or script_path, not both; use batch_cards for long jobs; never replay an unconfirmed timeout. Lacks explicit when-not-to-use beyond the batch_cards pointer.

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