open_script

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

Annotations already declare destructiveHint=true and readOnly=false; the description adds the concrete behavior behind that: refusal on unsaved changes and the fact that discard_changes overrides it, which tells the agent exactly what data loss looks like. Return-value behavior is left to the output schema.

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?

Two sentences, no filler: the action first, then the conditional guard. Every clause earns its place and the safety-critical condition is front-loaded after the primary action.

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 two-parameter mutation tool with annotations carrying the safety profile and an output schema covering return values, the description covers the essential gap: the refusal condition and the destructive parameter. Adequate without repetition.

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%, so the description carries the burden; it explains discard_changes precisely, including its default-off implication ('unless ... is true'). The path parameter is self-evident from its name, so no further detail is needed.

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: 'Open a .nk script in the live Nuke session.' That distinguishes it from save_script and the node-editing siblings without ambiguity. It doesn't explicitly name an alternative, so 4 rather than 5.

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?

Implies the use case (loading a script into the live session) and states the guard condition under which it refuses, which is a useful when-it-won't-work signal. It never says when to prefer this over another tool or what prerequisites (e.g. running session state) are required.

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