compute_bar_metrics

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

With no annotations provided, the description carries the burden and clearly discloses the key behavioral trait that the tool does not assign signal labels and only returns numeric data. It also mentions it follows threshold descriptions in the skill, adding context about how the data relates to methodologies. It does not mention rate limits or side effects, but for a compute-only tool these are less critical.

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 two sentences, front-loading the core function with a specific metric list, then a valuable clarification about non-labeling. It is concise with no filler, and each sentence serves a distinct purpose.

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?

Given the tool's modest complexity, the description is complete: it lists the outputs (metric names and trend %), explains its role in VSA/Wyckoff analysis, and clarifies its non-labeling behavior. It does not describe the return format or exact trend % computation, but the absence of an output schema makes this a minor gap, and the reference to the skill fills some context.

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?

All three parameters (symbol, resolution, count) are fully described in the schema with types, defaults, ranges, and purpose (e.g., count warm-up requirement). The description adds context about the computed metrics but does not enrich parameter semantics beyond what the schema already provides, so the baseline score of 3 applies.

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 computes raw per-candle metrics (volume_ratio, spread_ratio, close_position, body_ratio) plus trend %, with a specific verb 'Tính' (calculate). It explicitly distinguishes itself from signal-detection siblings by stating it does NOT auto-label signals, making its purpose unambiguous.

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 clear usage context: it is the objective foundation for identifying VSA/Wyckoff events, and it explicitly says conclusions are left to Claude based on the methodology skill. This implies when to use it (raw data needed) versus signal-labeling tools, though it does not explicitly name alternatives or state when not to use it.

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