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

Annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) cover the safety profile, and the description adds rich non-structured behavior: 1–3 minute runtime, a 50 s wait then jobId return, and the polling cadence. The luck-template pay-weight explanation (relative weight, not LP, priced from measured odds) is genuinely valuable context beyond annotations, though the certification.outcomes[].multiplierX100 reference is terse.

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?

Despite being information-dense, everything is front-loaded: purpose first, then timing/async contract, then the pay caveat last. Not a wasted sentence — each clause answers a question the agent would otherwise have to guess at.

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?

Covers invocation, latency, async handoff, follow-up tools, and a subtle output semantic; no output schema exists but the description explains the return (jobId). The one gap is sibling differentiation among the design_* tools, which leaves some ambiguity about when this is the right choice.

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 explains base, baseId, change, description and multiplayer. The description only adds the multiplayer room-size detail (up to 20 live rooms); otherwise it restates the schema's edit-vs-create semantics. Baseline 3 applies when structured fields do the heavy lifting.

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?

Starts with a specific verb+resource: 'The AI invents a new kind of game from your description ... writes its code and tests it.' It also scopes the modes (luck or skill, solo or multiplayer live rooms) so the agent can tell what output type to expect.

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 clear operational sequencing: call this, poll invent_status every ~10 s, then publish_invented_game, and notes via base/baseId that it doubles as an edit path. It does not explicitly contrast against design_skill_game or design_luck_board, which look like adjacent alternatives an agent might confuse it with.

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