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

No annotations exist, so the description carries the burden and mostly does: it discloses the lookback window, the exact result fields, a sample result row, and a per-call price of $0.05 USDC. It omits behavior on unknown GPU names, whether limit may exceed 30, and the currency/unit conventions behind the price fields.

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?

One front-loaded sentence defines the resource and the returned fields, followed by a concrete example and a one-line cost note. Every element earns its place; the example does the heavy lifting for format without extra prose.

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 output schema and no annotations, the description compensates well by enumerating the returned fields and showing a sample row. Remaining gaps are secondary: how to resolve valid GPU names and error/edge behavior.

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 coverage is 0%, so the description must compensate, and the example (gpu='H100 80GB', limit=7) conveys both the GPU name format and that limit truncates the number of returned days. It does not name an authoritative source for valid gpu values, though list_gpu_models is a sibling that would serve that role.

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 with an exact scope: a 30-day daily price series per GPU, enumerating the returned fields. An agent can immediately separate it from gpu_price (current snapshot) and market_movers (aggregate movers) without opening the 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?

The 30-day time-series framing implies when to pick this over gpu_price, and the worked example shows the intended call shape. However, it never explicitly names an alternative or states exclusions (e.g., 'for the current price use gpu_price').

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