List GC functions

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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely new context: it requires an active-client, has cost=medium, depends on the getgc capability, produces bounded-candidates, and points to tool-schema on failure. No contradiction with annotations.

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 and the 'useful for' clause are front-loaded, but the trailing Signature/Phase/Cost/Capabilities/Produces/Safety/On-failure tag block is listy and partly duplicates structured fields (the Signature repeats the schema). It is information-dense but not maximally economical.

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?

With no output schema, the description steps in by naming the returned fields (name/source/line/upvalues) and adds prerequisites (active-client), cost, and failure routing. That covers most of what an agent needs, though it omits result ordering/pagination behavior for what is implicitly a bounded candidate list.

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% and each parameter has its own description, so the schema carries the semantic load. The description only re-lists the parameter names/types in a Signature line without adding format, matching behavior, or default details beyond the schema. 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 specific verb (enumerate), a specific resource (live Lua closures from getgc()), and the return content (debug metadata: name/source/line/upvalues). This clearly separates it from siblings like list-gc-tables and list-gc-threads, which enumerate different object classes.

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 a concrete use case: 'live reversing when script paths are unknown.' However, it never names an alternative or a when-not condition, despite close siblings such as filter-gc, search-gc-value, or scan-closures-by-name that an agent might weigh against this.

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