tv_get_indicators

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

With no annotations, the description carries the full disclosure burden and does add useful behavioral context: RSI divergence flags, Bollinger squeeze detection, ATR stop_long/stop_short levels, the [-1,+1] composite score range, and what each optional flag produces. However, it does not reveal the return shape, that the indicators parameter defaults to ['all'] so every call computes the entire indicator set, or any data-source/error behavior.

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?

Two dense sentences of roughly 60 words with the core purpose front-loaded and no filler. Parameter names are embedded inline (include_weekly=true, benchmark_symbol, include_score=true), making the text directly actionable for an agent without cross-referencing the 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?

For a 20-parameter tool with no output schema and no annotations, the description thoroughly covers the feature and option matrix but omits the output contract: what the response contains, how weekly/benchmark/score fields appear in results, and that the default is to compute all indicators. An agent can select the tool confidently but would invoke it without knowing what it returns.

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 only 25%, so the description must compensate. It maps the three optional features to their parameter names inline (include_weekly=true, benchmark_symbol, include_score=true) and its indicator inventory aligns with the indicators enum values. The many numeric tuning parameters (macd_fast, atr_length, sma_periods, etc.) are left to their self-explanatory names, which is passable but adds no real semantic depth.

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 description opens with a specific verb and resource ('Compute technical indicators for any symbol') and enumerates the full indicator surface: RSI, MACD, Bollinger Bands with squeeze detection, EMA, SMA, ATR with stop levels, Stochastic, ADX, OBV, volume MA20/ratio, and RSI divergence flags. The sibling names (tv_get_historical_data, tv_get_quote, tv_screener) make this tool's distinct role unambiguous even without explicit comparison.

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 opening sentence establishes a clear selection context: use this tool when computed indicators are needed, as opposed to raw bars (tv_get_historical_data), a snapshot quote (tv_get_quote), or universe filtering (tv_screener). It stops short of naming those alternatives explicitly or stating when not to use this tool, but the purpose is specific enough that an agent can route correctly.

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