Find scripts that are hiding

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, so safety is covered. The description adds genuinely new behavioral context: the getscripts/getrunningscripts dependency, graceful degradation with a clear error, cost=medium, and the shape of each result. It does not, however, describe pagination or result-size bounds for maxScan=6000.

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?

The hiding criteria and use case are front-loaded and easy to scan, but there is some redundancy at the tail: 'Safety: read-only' duplicates readOnlyHint and 'idempotency=read-only' repeats the same idea twice. Otherwise well organized and information-dense.

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 read-only orchestration tool with no output schema, the description covers the dependency, the failure mode, and what each result contains (name, class, actual location, running status). Enough to call it correctly; only the maxScan tradeoff/truncation behavior is left implicit.

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 100%, so the schema already documents maxScan and threadContext fully. The description only restates the signature and defers to tool-schema for defaults and constraints, adding no meaning beyond the structured fields. Baseline 3 is appropriate.

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?

The description names a specific verb+resource (scan scripts and report the ones hiding) and enumerates the exact hiding criteria: nil-parented, detached from DataModel, running inside an Actor, living in CoreGui, destroyed-but-still-executing. This distinguishes it cleanly from siblings like find-running-scripts, find-detached-instances, and find-hidden-instances.

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?

It states the go-to use case (finding malicious/obfuscated/anti-detection scripts) and a prerequisite (requires getscripts/getrunningscripts, degrades with a clear error otherwise). It does not explicitly name sibling alternatives like find-running-scripts or find-hidden-instances, but the context for when to reach for it is clear.

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