List all string constants (IDA Strings window)

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds real context beyond them: prerequisite capabilities (getgc + getconstants), that the scan is capped and truncation is flagged, that results are sorted by reference frequency, and the failure path (inspect tool-schema). The 'idempotency=read-only' line merely restates the annotations, keeping this below a 5.

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 opening purpose and pivot sentence are strong and front-loaded, but the trailing metadata block (Signature, Phase, cost, idempotency, Requires, Produces, Safety, On failure) pads the definition and partly restates the schema and annotations. The Signature line in particular is redundant and less accurate than the schema it summarizes.

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 carries the return-shape burden and does so reasonably: it states each result is a unique string with an xref count and a sample owning script, sorted by frequency, and that truncation is flagged. Prerequisites and failure handling are noted, leaving little an agent needs missing to invoke 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 documents all five parameters including defaults and meanings. The description's 'Filter by substring and minimum length to cut noise' and its Signature line duplicate that content, with the signature actually being less precise (any? vs the schema's integer types), so it adds no meaning beyond the schema.

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 exact scope: 'Walk every Luau function in the GC and collect their string constants.' It gives a memorable analogy (IDA's Strings window) and names the natural next-step sibling (find-string-xrefs), so an agent can place it against list-gc-functions, search-gc-value, and find-functions-by-constant without opening 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?

Clearly frames the use case (finding literals like remote names, URLs, anti-cheat tags) and the follow-up pivot to find-string-xrefs, plus how to trim noise via filter/minLength. It stops short of explicit when-not-to-use guidance or contrasting itself with the closest alternatives such as find-functions-by-constant or find-string-in-tables.

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