cpu_get_market_index

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

With no annotations provided, the description carries the full disclosure burden and succeeds: it reveals the server-cached staleness, defines null price as 'no trades' rather than zero/free, explains that settled trades remain in the window even if the lot was later sold out/cancelled/evicted, and notes the spark series appears only in the JSON block. None of these behaviors are inferable from the schema or tool name.

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 purpose is front-loaded in the first sentence, and every subsequent sentence delivers a distinct, decision-relevant fact. However, at roughly eight sentences for a zero-parameter read tool, it is on the verbose side, and the 'never combined into one call' warning partially restates the cpu_get_markets differentiation from the previous sentence.

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?

Despite no output schema, the description equips the agent to interpret the response fully: per-resource row structure, volume unit semantics, reading trends from changePct, null-price handling, and staleness limits. The explicit contrast with cpu_get_markets completes the selection context, so no further lookup is needed to call or interpret this tool correctly.

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 explicitly confirms 'no inputs,' removing any ambiguity about invocation. There are no parameters for the description to elaborate on beyond that.

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 opening sentence states exactly what the tool returns — a world price index, one row per resource — and pinpoints the three metrics (24h volume-weighted average price in $CPU per unit, 24h percent change, 24h volume in resource units). It also actively distinguishes itself from the sibling cpu_get_markets by spelling out the different question each answers.

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?

The description gives an explicit when-not-to-use rule: 'do not use it where you need second-fresh data' because it is a server-cached aggregate that can run an hour behind. It names the alternative (cpu_get_markets), explains the exact difference (cheapest ask right now vs what the world actually paid over the last day), and adds a hard exclusion — the two are never combined into one call.

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