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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds real value on top by disclosing the polling cadence, the state machine (pending/ready/failed) and the interpretation caveat that outcomes[].pay are relative weights while multiplierX100 is the actual payout. It stops short of stating rate limits or what happens if a job expires or the id is unknown.

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 polling protocol are front-loaded in the first two sentences; the third sentence on pay/multiplier semantics is long but earns its place by preventing a misreading of the returned template. Slightly dense but no filler.

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 must explain return values itself, and it does: it lists each state and what accompanies it (progress, template plus certification, problems) and even how to read the pay fields. Nothing needed to call or act on 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?

There is a single required parameter with 100% schema description coverage ('From invent_game'), so the schema already carries the semantics. The description references invent_game as the source but adds no format, example, or validity detail beyond it, which is the baseline for a fully documented one-param 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?

The description names a specific verb+resource (checks an invent_game job) and enumerates the three terminal states with their payloads, which cleanly distinguishes it from siblings like get_invented_game and game_status. An agent can tell what it returns without opening any 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?

It gives an explicit trigger ('Call it every 10 s or so after invent_game'), an exit condition ('until it's ready'), and the exact next tool to invoke ('then publish_invented_game'). When-to-use and the alternative are both named rather than implied.

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