script

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description adds real value on top by disclosing that PRINT output is captured, that a mid-script failure reports the failing command with earlier commands already applied, and that dialog-opening scripts hang. That partial-effect warning is exactly the context a destructive tool needs. It stops short of noting reversibility or permissions.

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?

Four short sentences, front-loaded with what the tool does, followed by output and failure behaviour. The final sentence about dialogs is longer than needed but earns its place as a real hazard warning.

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 five-parameter, potentially destructive execution tool with no output schema, the description covers the return value (PRINT output), the error shape, and the blocking caveat. Gaps remain around argument passing and the wait_s/deadline_s split, which the schema covers but the description never reconciles.

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 the baseline applies and the description adds little: it only reinforces the path-vs-text choice already documented. It says nothing about 'args', 'deadline_s', or how 'wait_s' interacts with 'wait for it to end' — the latter is slightly at odds with the schema's note that the call may reply 'Running' while work continues.

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 and resource ('Run a PRACTICE script') plus the two input modes (file or text) and that it blocks until completion. It implicitly separates itself from single-command siblings like command/evaluate by emphasising script execution, but never names an alternative, so differentiation is left to inference.

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?

Usage is only implied: multi-step scripts should go here rather than through command/evaluate/run, and scripts that show dialogs are ruled out. There is no explicit statement of when to prefer this over the four sibling execution tools, nor prerequisites such as needing an open session.

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