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

With no annotations, the description carries the full burden and does disclose useful behavioral traits: the data source (TradingView screener), freshness (live), a latency figure (~0.2s), the default scope (top 12 majors) and a hard cap (up to 20 symbols). It omits rate limits, failure behavior for invalid tickers, and whether composite bias recalculates per-symbol, so it stops short of a 5.

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?

The output-field list is front-loaded and information-dense with little padding. But the final clause, 'Use for TA', is an unfinished sentence that dangles rather than instructing, and the long parenthetical could be split for easier scanning.

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?

No output schema and no annotations mean the description must cover returns and behavior, and it does describe the returned fields and the composite bias/trend tag vocabulary well. The remaining gap is mechanical: nothing reconciles the described ?symbols input with the empty, additionalProperties=false schema, which leaves an agent unsure whether it can pass filters at all.

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?

The description explains the ?symbols parameter thoroughly (cap of 20, default 12, BINANCE pairs, bare tickers like HYPE or full BINANCE:HYPEUSDT). However, the input schema declares zero properties with additionalProperties=false, so the only documented parameter cannot be expressed through the schema — an agent must guess it appends a query string. The semantics are good but contradict the structured contract, so the 0-param baseline of 4 is not warranted.

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?

A precise verb+resource statement: a TradingView technical-analysis snapshot for crypto, with the exact fields it returns enumerated (per-timeframe ratings, RSI, ATR/ATR%, 24h change, volume, 52w range, composite bias, trend tag). It is highly specific, but never names or contrasts against any sibling (akari_confluence, akari_deep, akari_market_report, akari_trade_plan), so the agent must infer where this sits versus those.

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?

Usage guidance is a truncated fragment, 'Use for TA', which adds essentially nothing beyond the name. No when-to-use conditions, no when-not, no named alternatives among the 19 sibling tools that plausibly overlap (akari_confluence, akari_trade_plan, akari_market_report).

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