Find hidden / detached instances

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

Annotations already cover read-only/idempotent/destructive, and the description adds real behavioral context beyond them: dependency on getinstances with graceful degradation, that results are bounded/capped samples with a full byClass tally, a maxScan cap that sets a truncated flag, and cost/phase metadata. It also describes the exact sample shape (class, name, path, location) and the meaning of 'hidden' (__inTree false), which is not in the 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?

The purpose is front-loaded and the sentences are information-dense, but the trailing metadata block ('Phase: observe; cost=medium; idempotency=read-only. Requires: active-client. Produces: bounded-candidates. Safety: read-only.') is boilerplate that largely duplicates the annotations and adds length without new meaning.

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?

There is no output schema, yet the description fully specifies the return shape (per-class byClass tally plus capped samples with class/name/path/location), the definition of a hidden instance, the getinstances dependency, and failure behavior. For a 3-param read-only tool this leaves nothing an agent needs to call it correctly.

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 fully documents limit, maxScan, and threadContext with defaults and clamping behavior. The description only restates the signature and mentions the capped-sample and truncation concepts, adding no syntax or semantics the schema does not already provide. Baseline 3 applies.

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 precise verb and resource: 'enumerate EVERY instance the executor can see... and report the ones that are hidden', then defines hidden operationally (nil-parented, detached, buried in Actor/CoreGui; __inTree is false). It explicitly positions itself as 'the broadest sweep', which distinguishes it from narrower siblings like find-detached-instances or get-nil-instances without needing to open their schemas.

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 clear context for use ('broadest sweep for anything an exploit/anti-detection script has stashed off the normal hierarchy') and a prerequisite ('Requires getinstances; degrades with a clear error otherwise'). It stops short of naming when-not-to-use or naming the narrower alternative tools, so the agent must infer the boundary between this and find-detached-instances/get-nil-instances.

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