cpu_upgrade

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

With no annotations, the description carries the full behavioral burden and succeeds: it discloses the full $CPU cost with auto-approval, immediate install plus a fresh construction timer, the contract's authority over successor validity, active processes, cooldowns, and storage, and post-upgrade state (deposits, balances, mode persist; production and Hub unavailable until done). This level of side-effect disclosure is well beyond typical mutation-tool descriptions.

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?

About 150 words, with every sentence carrying operational content: purpose, prerequisite, target-selection rule, cost, execution semantics, chain authority, persistence, and follow-up. It is front-loaded with the action and organized from prerequisites to side effects to verification, though the density makes it longer than typical tool blurbs.

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 2-parameter tool with no annotations and no output schema, the description is thorough: it covers prerequisites, cost, timing, persistence, availability consequences, and the verification path via cpu_get_cell. The one gap is the return value or response shape, which is not stated — partially mitigated by the explicit inspection suggestion.

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% and both parameter descriptions are already detailed, establishing a baseline of 3. The tool description restates the predecessor rule and dynamic-catalog resolution but adds little beyond the schema, only reinforcing tokenId as a Land cell — so it does not push meaningfully past the baseline.

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?

Names a specific action ('Upgrade') on a specific resource ('the building on a Land cell you own to a dynamically configured target type'). Explicitly routes predecessor-less base buildings to cpu_build, differentiating this tool from its closest sibling without requiring schema inspection.

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 concrete selection rules: authenticate with cpu_authenticate first, pull valid targets from cpu_get_game_config, and use cpu_build for base types with no predecessor. Also sets expectations that the tool performs no local validity pre-checks, so a stale local view should not deter a call, and directs the agent to cpu_get_cell to inspect the resulting construction.

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