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

Annotations already declare readOnly/idempotent/non-destructive, so the description is not carrying the safety burden; instead it adds operationally decisive facts the annotations cannot express: parameter-mismatch refusal, per-indicator return field sets, 7-day/free-key window, and the exact failure mode DP403_PLAN_REQUIRED when a finer interval or deeper start runs without a paid key. It also warns that smoothing requires leading periods before values are trustworthy, which materially changes how results should be read.

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 with purpose, then usage, then return shape, then caveats — the ordering an agent needs. It is dense but not padded; the one inefficiency is the trailing parameter recap, which repeats defaults already documented at 100% schema coverage and could be trimmed without loss.

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, enum-bearing, plan-gated analytics tool, the description covers everything an agent needs to call it correctly: which param belongs to which indicator, paging vs. start exclusivity, output field names per indicator, and price-level interpretation guidance (RSI 70/30, MACD histogram sign change). An output schema exists, yet the description still names the per-indicator fields, which is surplus rather than a gap.

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 earns above that by adding cross-parameter rules the schema does not encode — 'a parameter that belongs to another indicator is refused', 'cursor ... not with start', and the default-window behavior ('without start you get the last limit values'). Its verbatim restatement of defaults and start formats largely duplicates the schema, keeping it off 5.

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?

Names a specific verb and resource ('Get a technical indicator ... for one pool') and enumerates the five supported indicators in parentheses. It also draws a hard line against the nearest sibling by stating the values follow the pool's price 'as getPoolOHLCV reports it, with no inversed parameter', so an agent can separate this from getPoolOHLCV and getTokenIndicator 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?

Gives concrete trigger utterances ('is this pool overbought?', 'RSI of this pair', 'MACD cross on the last candle') and an explicit alternative with a reason to prefer this tool: 'instead of fetching getPoolOHLCV and computing the indicator yourself'. Preconditions (keyless vs keyed, 7-day history, interval >= 10m on a free key) are stated up front rather than left to inference.

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