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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds real operational context the annotations lack: the unbounded default window produces an oversized response, which is effectively a result-size warning.

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?

Three tight sentences: identity, then parameter conventions, then the resolution tradeoff. The most consequential guidance (always pass tf and from) is front-loaded and every sentence carries information.

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?

For a read-only, five-parameter, flat-schema tool with no output schema, this covers identification, required conventions, and response-size risk. The only gap is no hint at the shape of a candle record, which an agent might want since no output schema exists.

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 100%, so baseline would be 3. The description goes beyond it by stressing that from/to are unix SECONDS and that tf and from should always be supplied, converting schema facts into practical calling advice, plus a resolution tradeoff for long windows.

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 verb and resource: OHLCV candles for a single token identified by chain slug and contract address. It clearly implies the token scope (versus a perp market), though it never names the sibling get_perp_candles explicitly.

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 gives concrete when-to-use direction: always pass tf and from, and use a coarse tf (60, 1D) for long windows, with the reason (over a thousand bars otherwise). It stops short of naming alternatives such as get_perp_candles for perp data.

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