cpu_craft

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

With no annotations, the description carries the full burden and excels. It discloses that inputs are debited upfront, most recipes start timers immediately, forge_wcpu has a one-time unbounded $CPU allowance and waits for confirmation, switch costs are burned for recipe changes, and the result reports both costs separately.

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?

Every sentence carries useful information, but the single dense paragraph is long and somewhat rambling. It is front-loaded with purpose and prerequisites, yet tighter structuring could improve readability without losing content.

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 complex execution tool with no annotations, no output schema, and 3 parameters, this description is remarkably complete: it covers prerequisites, recipe discovery, pricing checks, cost/approval details, switch behavior, timer semantics, progress tracking, and claiming.

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?

Even though schema coverage is 100%, the description adds substantial meaning: 'batches' behavior (upfront debit, no cancel), the forge_wcpu auto-approval and cost specifics, switch cost semantics, and the requirement that the tokenId must be a cell the user owns. This goes well beyond the schema's field descriptions.

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 opens with a specific verb+resource: 'Run a craft recipe on a cell you own (refine raw resources, or forge $WCPU).' It clearly distinguishes this execution tool from related sibling tools like cpu_get_craft_status, cpu_claim_craft, and cpu_list_recipes.

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?

Explicit usage guidance is provided: 'Requires a session — call cpu_authenticate first; discover recipes with cpu_list_recipes' and 'Check the price per recipe in cpu_get_cell (outputs) before you commit.' It also names the follow-up tools (cpu_get_craft_status, cpu_claim_craft), making the workflow clear.

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