Turn a natural-language goal into a tool workflow

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

Annotations already cover read-only/idempotent/non-destructive, so the repeated 'READ-ONLY'/'Safety: read-only' lines add little. However, the description adds real behavioral context: what signals it fuses (intent aliases, live catalog, schemas, mutation flags, recipes), that the output is a starting point rather than a final answer, and the failure path.

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?

Purpose is front-loaded, but the trailing templated metadata (Signature, Phase, cost, idempotency, Requires, Produces, Safety, On failure) is boilerplate that repeats the annotations and the READ-ONLY claim multiple times. Some sentences earn their place, several do not.

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?

No output schema exists, so the description carries the return-value burden, yet it only says 'Produces: agent-guidance' and 'ranked, schema-aware workflow' without describing the workflow's shape or fields. For a planning tool this leaves a meaningful gap, though the failure guidance partly compensates.

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 four parameters. The Signature line merely restates them with looser types ('any?') and adds no syntax or default detail beyond the schema. The only genuine value-add is the instruction to pass a natural-language goal, not a guessed tool name.

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 ('convert a vague Roblox goal into a ranked, schema-aware workflow') and differentiates from siblings by contrasting its role with tool-schema (which is for exact field inspection). An agent can immediately tell it apart from list-tools/suggest-tools.

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 explicit context ('especially useful for goals involving UI/input, remotes, player values, instance inspection, or reverse engineering') and names the follow-up alternative (inspect the exact schema of the selected tool; on failure use tool-schema). No explicit when-NOT-to-use, but strong routing guidance.

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