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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered. The description adds genuinely new context: the data is sourced from the token's deepest pool (a selection behavior the agent could not infer), volumes/derived metrics are computed from the candles, and each call costs $0.01. Return format details (pagination, candle shape) remain unstated.

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 dense sentence front-loads the resource and its distinguishing property, followed by a brief positioning clause and a terse cost note. No filler, no repetition of schema fields.

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, the description carries the burden of explaining returns and does so by naming the candle data and the four derived metrics. Combined with full parameter coverage in the schema and complete annotations, an agent has enough to invoke it correctly; only the concrete response/pagination shape is left unspecified.

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 100%, with each parameter documented including enum and defaults, so the schema carries the load and 3 is the baseline. The description adds only the 'deepest pool' sourcing note, which is more behavioral than parameter-specific; it adds no syntax or format guidance beyond the schema.

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+resource ('OHLCV candles for a token on any chain') and enumerates the derived metrics returned. It explicitly positions itself against the rest of the catalog ('the only time-series data in this catalog; every other endpoint is a point-in-time snapshot'), so an agent can separate it from check_token_price and get_token_snapshot without opening a 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 time-series framing gives clear context for when to reach for this tool versus the point-in-time snapshot endpoints. It also surfaces a cost signal ($0.01), which is a practical selection factor. There is no explicit exclusion or named sibling alternative, so it stops 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.