detect_macd_divergence

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses that the tool is a port of a personal alert engine backtested on real VNDIRECT data, and that it returns current status, newly generated signals at the latest candle, and signal history. However, it does not discuss limitations, potential false positives, data sensitivity (e.g., needing enough candles), or any side effects. This is moderate transparency but lacks important behavioral caveats for a detection tool.

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 description is a single, information-dense sentence that covers purpose, origin, and return values with reasonable efficiency. It is not overly long, but the multiple clauses make it slightly less scannable. A short list or second sentence would improve structure, but it is still appropriately compact.

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?

There is no output schema, so the description must explain what the tool returns. It does mention three types of return data (current status, new signal at latest candle, signal history) but does not describe the structure or format of these outputs (e.g., boolean, object, or array). For a specialized analysis tool, this is a notable gap. The description also omits any details about the 'lobe-based' algorithm, leaving the agent to infer the input–output behavior. It is adequate for a high-level understanding but not fully complete.

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 parameters (symbol, resolution, count) are fully documented in the schema. The tool description itself adds no additional parameter meaning beyond restating the purpose; for example, the note about 'count' needing to be large is in the schema, not the description. Therefore, the baseline of 3 is appropriate.

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 clearly states the tool detects MACD divergence (lobe-based) and reversal confirmation status for a Vietnamese stock, which is a specific verb+resource+scope. It is distinct from all sibling tools, none of which mention MACD or divergence detection. The mention of 'alert engine' and 'backtested' reinforces its specialized purpose.

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 description provides usage context by explaining the return values are meant for deciding whether to alert immediately ('dùng để quyết định có cần cảnh báo ngay không'). It also implies appropriate use through the resolution guidance in the schema ('1D cho tín hiệu swing, 1H/4H cho tín hiệu ngắn hạn hơn'), though this is in the parameter schema, not the tool description. It does not explicitly state when not to use this tool or name alternatives, but no sibling is a direct alternative.

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