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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, but the description adds genuinely non-structured behavior: server-side computation, 'keyless', values ordered oldest-first one per completed candle, cross-indicator parameters being refused, and the smoothing caveat that you must start ~10 periods before the first value you rely on. It stops short of describing pagination limits or error modes beyond the refusal rule.

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?

Front-loaded correctly — what it does, why to use it over the alternative, then return shape, then parameters. It is a single dense block that is longer than strictly necessary, and the interpretive guidance (RSI > 70 overbought, MACD histogram sign flip) could be trimmed or split, but nearly every sentence carries actionable content.

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 14-parameter, multi-indicator tool with an output schema and full annotation coverage, the description supplies the selection logic, return-field shape, interval/cursor caveats, and per-indicator parameter routing. An agent has everything needed to choose the tool and construct a correct call.

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%, so the baseline is 3; the description still earns credit by consolidating the per-indicator parameter mapping (period for rsi/ema/bbands/vwap, fast/slow/signal for macd, std_dev for bbands) and by adding the two behavioral rules the schema only hints at: pass interval every time, and cursor must not be combined with start. It omits the required rationale parameter, but that is fully documented in 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?

Opens with a specific verb+resource ('Get a technical indicator ... for one pool') and immediately scopes it to five named indicators computed server-side from the pool's OHLCV candles. It also differentiates itself from the nearest sibling by naming getPoolOHLCV and the pool-vs-token distinction implied by getTokenIndicator.

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?

Gives concrete trigger questions ('is this pool overbought?', 'RSI of this pair', 'MACD cross on the last candle') and an explicit alternative-plus-rationale: use this 'instead of fetching getPoolOHLCV and computing the indicator yourself.' The when-to-use case and the substitute it replaces are both stated outright.

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