TradingView-only: news sentiment

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

With no annotations, the description carries the full burden and does reasonably well: it discloses backend selection, that local scoring is deterministic/offline/free, that the payload self-reports its backend via `provider`/`scoring`, and that it never fabricates a score when there is no material. It stops short of stating failure behaviour (unknown symbol, empty feed) or latency/cost of the Marketaux path.

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 one-line summary followed by Args and Returns sections; every sentence adds information, including the backend-precedence rule and the no-fabrication guarantee. There is no filler or restatement of the tool name.

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?

An output schema exists, yet the description still helpfully sketches the envelope (TRADINGVIEW label, sentiment_score, label, bullish/bearish/neutral counts, strongest headlines). Combined with the backend disclosure, an agent has enough to call it correctly; only the sibling-routing and error cases remain uncovered.

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 0%, so the description must compensate, and it does: `symbol` is a ticker, `limit` is the number of headlines analysed, and `category` is explicitly flagged as applying only to the Marketaux path — a non-obvious constraint the schema does not convey. It could still note the valid category values, since no enum is declared.

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 states a specific verb and resource — news-based sentiment for a symbol — and names the concrete mechanism (Marketaux entity sentiment vs local VADER scoring of Finviz headlines). It does not, however, distinguish itself from the sibling `stock_news` tool, leaving the agent to infer that this one returns a score and that one returns articles.

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?

It gives a clear selection rule for the internal backends: Marketaux is preferred when MARKETAUX_API_TOKEN is set, otherwise local scoring is used, and it notes no API key is required. What is missing is external routing guidance versus alternatives such as `stock_news` or `stock_why_moving`, which would let an agent pick among siblings confidently.

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