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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), and the description adds substantial interpretive context: unit conventions (BTC per PH per day, not the USD/PH/day norm), that networkPhs is raw PH/s, and that medianAsk is the median of the bookSample subset rather than the whole book. These are exactly the non-obvious traits annotations cannot express.

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 clause carries either a unit convention or a routing instruction, so nothing is wasted, and the identity of the tool is front-loaded. It is a dense block of sentences rather than a scannable structure, which costs a point but not much.

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 parameters and no output schema, the description carries the full burden of explaining the returned data, and it does: units, the meaning of networkPhs, the sampling basis of medianAsk, and the aggregate-vs-own-price distinction. An agent has everything needed to call it and interpret the result.

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 are zero parameters, so the baseline is 4 per the rubric. The description instead clarifies the semantics of returned fields (hashprice, networkPhs, medianAsk, bookSample), which is useful but not parameter documentation.

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 resource and scope: the live SHA256 AsicBoost hashrate rental market, with the aggregate third-party market as its subject. It also carves itself apart from siblings by pointing to list_available_rigs for own machines and get_quote for direct pricing, so an agent can distinguish it without opening a 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 explicitly states when NOT to use this tool and which alternatives to call instead ('for our own machines call list_available_rigs and for our direct price call get_quote'). It also warns that thirdPartyMarket is aggregate wider-market data, not Galaxy Mind's own price, which prevents a common mis-selection.

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