scan

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

Even with annotations already declaring readOnlyHint, the description adds substantial behavioral context: rate limits, timing estimates, six-hour bar caching, timeout risks when max_symbols is raised, result miss categories, data-absence semantics for volume, and truncation reporting. This is exactly the kind of operational detail that prevents an agent from misinterpreting scan output or misconfiguring a costly sweep.

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 dense but front-loaded with the core purpose, then organized into clear cost and result-semantics paragraphs. Every sentence earns its place by warning about timeout risk, caching behavior, miss interpretation, or truncation — all critical for correct invocation.

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?

For a complex 11-parameter tool with no output schema, the description supplies what an agent most needs to call it correctly: universe selection hint, cost and timeout ceilings, caching guidance, data-availability caveats, and explicit miss/truncation semantics. Combined with the rich input schema, this is sufficiently complete for safe and effective invocation.

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 coverage is already 73%, but the description adds meaning beyond the schema: max_symbols is tied to a concrete timeout/cost ceiling, overlays like sma200 carry disproportionate cost, and left/right are illustrated with examples like close and sma20. The description does not add much for op, panels, or overlays beyond the schema enums, so it does not fully close every parameter gap.

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 specific action and resource: 'Run a condition across many IDX stocks at once.' It also distinguishes the tool from alert_check by framing scan as 'alert_check for stocks you have no rules for,' giving an agent an immediate way to separate it from a key sibling.

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?

It clearly positions scan relative to alert_check and gives operational guidance: sweep broadly once, then iterate because of caching. It also notes that the watchlist universe is 'usually the one you want.' However, it does not explicitly contrast scan with other sibling screening tools like screener or technicals, so it stops short of full exclusion guidance.

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