What every number for one asset was on a past day

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

Discloses critical behavioral traits beyond raw schema: each row is a single reading at takenAt, not a daily open/close/average; the job runs hourly and rewrites the current day's row; coverage reports days on record and history starts when the snapshot first ran; null means 'not read that day' rather than zero. It also explains unit semantics for dexPremiumPct and totalSupplyRaw and the ERC-8056 multiplier difference between Chainlink price and bid/ask. There are no annotations to contradict.

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 description is dense and information-rich, front-loading the core purpose and then providing necessary caveats and unit semantics. A few sentences are long, but every sentence earns its place given the complexity of the data. It could be slightly tightened, but remains efficient for the volume of behavioral nuance it conveys.

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?

Completeness is strong given the tool's complexity and the absence of an output schema. The description explains the row's meaning, time semantics, coverage, and key unit differences. While it doesn't enumerate every output field in prose, the schema already covers parameter definitions and the example plus field list adequately set expectations.

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 already high (83%), and the description adds semantic detail for the 'at' parameter with an example, explains the window with from/to or days, and clarifies the meaning of 'coverage' and 'fields'. It does not restate the standard string formats, but the example and explicit date-window hints give the agent meaningful extra context.

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 clearly states the tool returns a daily snapshot per asset with an explicit list of fields, and uses a concrete example query ('what was TSLA's premium on that day') to show how to use the at parameter. It distinguishes this from related tools by specifying it is historical daily data, not status or feed rounds.

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?

Provides explicit guidance on when to use the tool: to answer questions about a past day's values per asset, with at=YYYY-MM-DD, from/to or days for a window, and fields to narrow rows. It also clarifies the data's daily nature, coverage caveats, and the distinction between reading takenAt versus a daily open/close/average. It doesn't explicitly name sibling alternatives, but its context is strong enough to route an agent correctly.

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