norns_stop_script

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

With no annotations, the description carries the full burden and does well: it leads with 'WRITE', names the destructive effect (script stopped, engine freed), and discloses the safe default (dry run) plus the explicit confirmation gate for real execution. It stops short of saying what happens to in-memory state/params or what occurs if no script is running, which are the remaining behavioral unknowns.

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?

Front-loaded with the 'WRITE' safety marker, then the action, then the invocation rule — three short clauses with zero filler. Nothing could be removed without losing safety or invocation information.

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 one-parameter mutation tool with an output schema (so return values need no explanation), the description covers the action, the default safety mode, and the confirmation requirement. It is nearly complete; only edge behavior (no script running, whether script state is discarded) is unaddressed.

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 description coverage is 0% and the single 'confirm' boolean has no description, so the description must supply its meaning — and it does, by tying confirm=true to live (non-dry-run) execution. The only defect is the dangling '--live' token, which describes a flag the schema does not expose and slightly muddies the parameter story.

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 ('Stop the running script and free its engine') and adds a concrete analogy (K1+K3 'stop' on the home menu) that pins down the exact semantics. The verb 'stop' cleanly distinguishes it from siblings like norns_start_script and norns_load_script.

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?

Gives the operative invocation rule: it is a dry run by default, and going live requires confirm=true. That tells an agent how to safely call it without extra discovery. However, it never names alternatives or states when not to use it, and the reference to '--live' has no counterpart in the schema, which could send an agent looking for a nonexistent flag.

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