Scan GC tables for numeric values in a [min, max] range (CE range scan)

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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds substantial extra behavior: pcall-guarded iteration so locked/proxy tables never abort, NaN skipping, maxScan/limit caps with a 'truncated' flag, and a getgc(true)->getgc() fallback. These are exactly the operational traits an agent needs beyond the 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?

Front-loaded with the core operation and the key alternative, and most sentences carry real content (bounds semantics, next-scan technique, return shape). However, the trailing tag block ('Phase: observe; cost=high; idempotency=read-only', etc.) partly restates the annotations and adds some padding against an otherwise dense description.

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 supplies the return shape ({ min, max, matchCount, scannedObjects, truncated, matches } or { error }), the resource caveat (requires getgc), and the follow-up tooling. For a high-cost, complex scan tool this is sufficient to invoke and interpret 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 coverage is 100%, so the schema already documents all five parameters including defaults and bounds, which sets the baseline at 3. The description reinforces limit/maxScan capping and the truncated behavior but adds little syntax or meaning beyond what the schema descriptions already state, and gives only a bare signature with types.

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+resource with scope: 'walk every live Luau GC table and report each numeric value v where min <= v <= max'. It explicitly distinguishes itself from the sibling search-gc-value by framing itself as the 'inexact complement' that does not need the precise number. An agent can tell it apart from find-string-in-tables and search-gc-value without opening a schema.

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 concrete when-to-use conditions ('when you know a stat is within a window but not its exact value') with examples, names the alternative it complements (search-gc-value), and describes the follow-up workflow (successive tightening scans, then read-path-value / write-path-value). When and why are fully specified with no inference required.

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