Create a new game

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

Annotations only declare the safety profile (not read-only, not destructive, not idempotent, closed-world); the description adds what they cannot: writes to local disk only, requires no login, aborts on a non-empty folder, and returns the written files. The per-template build semantics (no build step vs. `npm install && npm run build` -> dist/) are behavioral detail an agent needs before scaffolding.

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 and the alternative-routing sentence are front-loaded, and every following sentence adds a distinct fact (local-only, overwrite guard, return value, template table). The nested parentheticals in the template list are dense and occasionally run-on, costing a point on readability but not on substance.

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?

For a three-parameter scaffolding tool with no output schema, the description still covers return content ("Returns the files written"), auth posture, failure mode, and post-scaffold build steps per template. Nothing an agent needs in order to call it correctly or interpret the result is missing.

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% and already documents dir, title bounds, and the template enum with a default, so the baseline is 3. The description earns an extra point by explaining the consequences of each template choice (plain JS vs. Vite build output vs. BroadcastChannel multiplayer stand-in), which the enum list alone does not convey.

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?

"Scaffolds a new minimal game, already integrated with the Gamealia SDK, into an empty or new folder" gives a specific verb, artifact, and target, and the "local files only, no login" clause separates it from the account-bound siblings. The explicit contrast with gamealia_analyze_project + gamealia_integrate_sdk makes it distinguishable without opening either 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?

States the trigger condition ("when there is no game yet") and names the two-step alternative it replaces, which is exactly the routing decision an agent faces. The guard "Never overwrites: fails if the folder has any file" tells the agent when the call will not succeed, which is a usage constraint, not just a behavior.

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