suggest_indicator

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

The description discloses that the tool uses a pure keyword heuristic with no LLM call, setting expectations for behavior. It does not provide details on return structure or error cases, but given no annotations, the description adequately covers the key behavioral trait of being a simple mapping.

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 three sentences, each providing distinct value: specifying intent examples, usage condition, and a note about heuristics and follow-up. It is front-loaded with the most critical information first and contains no redundant phrases.

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?

The tool has two parameters, no output schema, and no annotations. The description covers input semantics and usage guidelines but lacks detail on output format (e.g., indicator names, ranking). However, it suggests using list_indicators for confirmation, somewhat mitigating the gap.

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?

Both parameters have schema descriptions, and the description adds context by explaining the mapping from description to indicators and the purpose of k as ranking count. The schema already covers the parameter definitions, so the description enhances meaning with usage examples.

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 explicitly states the tool recommends FLOX indicators based on a natural language description, providing example intents. It distinguishes from siblings by noting it should be used when the user describes intent without naming an indicator, differentiating from tools like list_indicators or compute_indicator.

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 specifies when to use: 'Use this when the user describes what they want without naming an indicator.' It also advises against relying on LLM by stating it's a pure keyword heuristic, and directs to confirm with list_indicators after selection.

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