get_action_signals

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

With no annotations, the description carries the transparency burden. It discloses the statistical basis (Granger causality, p-value), the specific data inputs (live GDI and SMI data), and the output format (statuses). It also notes the paid-tier access restriction, which is a meaningful behavioral constraint. However, it does not mention whether the tool has any side effects, rate limits, or response structure details, but for a read-only data retrieval, this is adequate.

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 exactly three sentences, each contributing distinct value: purpose/data, statistical definition, and output/access. It is front-loaded with the main action and resource, and every sentence earns its place without redundancy. This is model conciseness.

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 no output schema, the description adequately explains what the tool returns: 'ACTIVE, WATCH, or CLEAR status for each signal.' It also explains the signal's characteristics (lag time, directional accuracy, p-value), giving the agent enough context to anticipate the response. With zero parameters and no output schema, the description fully covers the required information.

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 tool has zero parameters, so the baseline score is 4. The description adds no parameter-specific information, but none is needed since the input schema is empty. The description's context about data sources and signals indirectly explains what the tool expects (no manual input required).

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 specifies the tool's function: 'Get statistically validated leading indicator signals evaluated against live GDI and SMI data.' It distinguishes from sibling tools by referencing specific data sources (GDI/SMI) and the statistical methodology (Granger-causal, p≤0.01). The return statuses (ACTIVE, WATCH, CLEAR) further clarify the exact output.

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 context on when to use the tool: when needing statistically validated signals from GDI and SMI data with lag time and directional accuracy. It implies a specialized use case without explicitly naming alternatives, which fits the 'clear context, no exclusions' level. The 'Paid tier only' note adds a usage restriction.

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