cpu_get_game_config

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

With no annotations, the description fully covers behavioral traits: it calls itself 'A free reference read' and states 'No session needed,' disclosing cost and auth requirements. It also explains that the randomness mode determines cpu_reveal behavior, adding useful context beyond a simple return-value list.

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?

The description is a single long but dense sentence followed by a short call-to-action. Every clause adds value, though it could be easier to parse if split into a list. It is not verbose.

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?

Given no output schema and no annotations, the description is complete: it lists the rulebook contents, explains the relationship to cpu_reveal, directs to cpu_list_recipes, and states that it is free and session-free. This fully equips an agent to use the tool.

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?

The tool has zero parameters, so the baseline is 4. The description instead elaborates on the returned data, which is appropriate; no parameter syntax is needed.

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 clearly states the tool returns the game rulebook for the active network, enumerating the resource catalog, building catalog, reveal-cost params, randomness delivery, contract addresses, and recipe count. It also distinguishes itself from siblings by mentioning cpu_list_recipes for the full recipe graph and how the result affects cpu_reveal.

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?

Provides explicit usage guidance: 'call it once to ground planning' and 'No session needed' indicate when and how to use it. It also names an alternative, cpu_list_recipes, for the full recipe graph, helping an agent choose between tools.

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