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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the genuinely useful non-obvious traits: it is a poll-until-terminal-state tool, the approximate interval, and which tool to chain into on success. It doesn't say what happens on an unknown/expired jobId, which is the one behavioral hole.

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 action and the three states, then the polling protocol, with no filler sentences. The closing clause on pay weights vs. multiplierX100 is somewhat tangential to a status poll but is dense, high-value context for the ready case.

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 return-value disclosure and does so reasonably: pending returns progress, ready returns template plus certification, failed returns problems. A brief note on invalid/expired jobId behavior would make it fully complete.

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 the only parameter is documented ('From invent_game'), so the schema already does the work. The description adds a little context about which AI builds the game but nothing about jobId itself beyond what the schema says; baseline 3 applies.

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 and resource ('checks an invent_game job') and enumerates the three possible states with what each carries, so the agent knows exactly what it gets back. It does not, however, distinguish itself from the sibling check_invented_game, which sounds near-identical from the name alone.

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 a concrete trigger condition ('after invent_game'), a polling cadence ('every 10 s or so'), and an explicit termination/next step ('until it's ready, then publish_invented_game'). It omits any guidance on when to prefer check_invented_game instead, which is the main ambiguity an agent faces here.

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