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

Annotations already cover read-only/idempotent safety, but the description adds real domain behavior: a fixed 20:00 UTC publication cadence, one settle per GPU and form factor, values never revised, 'no-settle' as an explicit marker for insufficient data, corrections as separate rows, oldest-first ordering, and a metadata.latest block with 1/7/30-day moves. It stops short of describing row fields or how the limit interacts with the 30-day window.

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?

Dense and front-loaded: the definition of the settle and its cadence come first, then edge cases, then ordering/window. The closing sentence about free and Pro tiers and the Datasets API is slightly cryptic but still carries routing value.

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 5 undocumented parameters, no output schema, and a data product whose shape matters, the description explains the result semantics well but leaves the request side underspecified — filtering by GPU/form factor, date bounds, and pagination behavior are all unaddressed.

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% across 5 parameters, so the description must carry the load. It only obliquely conveys the gpuModel and formFactor concepts ('one settle per GPU and form factor') with no value formats or examples, and says nothing about from, to, or limit semantics beyond the fixed 30-day window.

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 states a specific resource and semantics: an official daily GPU rental price settle, one per GPU and form factor, in USD per GPU-hour. It implicitly scopes itself against the broader history ('the full history is in the Gloom Datasets API') but never names gpu.history, gpu.board or gpu.changes, so an agent must still guess how this differs from its closest siblings.

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 is implied rather than stated: rows cover the last 30 days and the full history lives elsewhere, which hints at when this tool is the right one. There is no explicit 'use X instead when Y' and no statement of prerequisites for the from/to window, so routing still requires inference.

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