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

Goes well beyond the readOnly/idempotent annotations: explains the internal window widening and trimming so the first point is converged, that the window is measured back from the latest point so lagging feeds still return full windows, and which conditions return 400. Also proactively states VWAP is not offered and why.

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 organized by indicator families. It is lengthy, but nearly every sentence carries non-obvious constraints (atr OHLC requirement, resolution bucket bound, VWAP exclusion) rather than restating schema.

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 11 parameters, no output schema and mutation-free annotations, the description compensates fully by explaining the `lines` return structure keyed by line name for each indicator family and the warm-up/trimming behavior. An agent could call this correctly from the description alone.

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 91%, so the baseline is 3; the description adds real meaning by mapping parameters to indicators – which use `period` vs fixed spans, the 400-bucket bound on `resolution`, and the sma/ema/rsi vs bollinger/atr vs macd `period` defaults. The empty `asset_class` schema description is the main gap.

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 opening sentence gives a specific verb and resource ('Get a technical indicator series') and clarifies it is computed from close prices, distinguishing it from raw-price siblings like get_candles or get_price_history. It could more explicitly name the sibling boundary, but the resource is unmistakably different.

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?

Rich conditional guidance: atr requires tick-storing assets and returns 400 otherwise, momentum measures reject `period` and need coarse enough `resolution` to fit in 400 buckets, trending_ratio needs a CoinGecko-mapped asset and `resolution` of at least 1h. It lacks an explicit 'use X instead' routing sentence against siblings, 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.