compute_indicators

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

With no annotations, the description carries the full burden and does a solid job. It discloses output behavior in detail: returns each indicator's latest value(s) plus derived signals like state, cross, direction, flip, and signal. It also explains the effect of include_series. It does not mention potential errors or rate limits, but these are less critical for a read-only compute tool. It adds substantial behavioral context beyond what structured fields would provide.

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 long but well-structured: a one-line purpose, a concrete example, categorized indicator lists, and a paragraph on returns. The length is justified by the need to enumerate 73 indicators and their aliases. It front-loads the key information and does not ramble, though the sheer volume may be slightly overwhelming. Overall it is efficient for the complexity.

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 complexity, the description covers the essential aspects: input format, supported indicators, and return value semantics. It even notes special output flags (cross, state, direction). Since an output schema exists, the exact return structure need not be described. It does not mention error behavior or data requirements, but for a compute tool with rich output documentation, it is reasonably 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 0%, so the description must compensate. It thoroughly explains the most complex parameter (indicators): format, examples, aliases, and the full supported list. It also explains include_series. However, it does not explicitly describe symbol, timeframe, exchange, or limit; these are only implied by the opening phrase and parameter names. Given the complexity of indicators, the description partially compensates for the lack of schema descriptions, but leaves gaps for other parameters.

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 clear, specific verb+resource: 'Compute technical indicators for a symbol/timeframe.' It distinguishes itself from sibling tools that do higher-level analysis (e.g., detect_cross, detect_divergence) by focusing on raw indicator calculation. The extensive list of supported indicators further reinforces its unique 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 clearly implies when to use this tool (when you need indicator values or derived signals) but does not explicitly exclude alternatives or refer to sibling tools. For example, it mentions returning 'cross' signals, which overlaps with detect_cross, but does not say 'use detect_cross for event detection' or provide any when-not guidance. Thus the usage is conveyed but not contrasted with alternatives.

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