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

With no annotations at all, the description carries the full burden and does well: it discloses per-call pricing ($0.02 USDC), that billing covers filtering/sorting/formatting rather than the underlying data, and the licensing/redistribution terms of the raw source. It does not cover rate limits, auth requirements, maximum allowed 'days', or error behavior, which keeps it below a 5 for a paid tool.

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?

Front-loaded with what is exported and what fields come back, then the call example, then the pricing/licensing caveat — a sensible ordering with no filler sentences. The trailing billing note is longer than strictly needed but does earn its place by justifying the cost.

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?

No output schema exists, and the description compensates by enumerating every returned column and the two output formats, plus a concrete invocation example and the cost model. For a three-parameter, non-destructive export tool, an agent has everything needed to call it 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?

Schema description coverage is 0%, so the description must compensate, and it does for two of three params: 'gpus' is shown to be a comma-separated model list and 'fmt' is constrained to json or csv via the worked example. 'days' is only implied by the example value (7) and its default of 30 is never mentioned, nor is any upper bound.

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?

States a specific verb and resource: bulk-export daily price series for a set of GPU models over N days, with enumerated output fields (lowest price, market median, platform of lowest price, inventory status, quote count) and formats (json/csv). The 'bulk' framing implicitly separates it from the single-card gpu_price/gpu_history siblings, but it never names or contrasts bulk_snapshot_query, which an agent would need to choose between.

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?

Usage context is clear (multiple cards at once, date window, format choice) and it offers an explicit self-serve alternative: raw data can be downloaded free from the history.csv URL under CC BY 4.0, with the note that you pay only for pre-filtered/formatted results. It lacks an explicit rule for when to pick bulk_snapshot_query or gpu_history instead, so it falls short of a 5.

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