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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds the substantive methodological facts an agent cannot guess: the range is centered on the price at the window's start, not the current price, and the evaluation horizon is the trailing `days` 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?

One densely packed sentence with the operation front-loaded and the output metrics trailing after a colon. Every clause earns its place, though the density makes it slightly hard to scan.

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, enumerating fee APR, impermanent loss, net APR, time in range, and ticks in the description is the right call, and the anchoring/window semantics are covered. Minor gaps remain on result granularity and chain/pool compatibility.

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 75%, and the description supplies the missing semantics: `rangePct` is a half-width anchored symmetrically at the window-start price with 0 meaning full range, and `days` defines the observation window. It adds real meaning beyond the schema text rather than restating it.

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?

Specific verb (backtest) plus resource (a symmetric price range on a pool) and a concrete list of the metrics produced. It is clearly distinct from the list/get siblings, though it never names them.

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?

No when-to-use statement, no prerequisites, and no routing to alternatives such as get_pool for current (non-historical) data. Usage must be inferred from the verb alone.

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