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

Annotations include readOnlyHint=true, so the read-only safety is already disclosed. The description adds useful view-specific behavior (e.g., 'simulation-aware live GEX surface', 'raw OI simulator state') but does not go deeper into response structure, latency, or data freshness. It neither contradicts annotations nor adds significant behavioral context beyond what annotations already guarantee.

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 compact, three sentences long, and front-loaded with the core purpose. It lists contents first, then explains view-based usage, with every sentence contributing necessary information and no repetition or filler.

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 is moderately complex with multiple views and return components, and there is no output schema to clarify response shape. The description explains what data areas are included and how to select views, but it stops short of describing the output format or relationship to sibling tools. This is adequate for basic invocation but leaves the agent guessing about response structure.

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 100% and each parameter, including view, apiKey, and symbol, already has meaningful descriptions. The tool description largely mirrors the schema's view semantics, adding only slight conceptual framing like 'model input'. This adds marginal value beyond the schema, so the baseline score of 3 is appropriate.

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 uses a specific verb-resource structure: 'Headline flow bundle in one call', and enumerates exactly what the bundle contains (OI state, levels, GEX/DEX totals, pin-risk, dealer-risk). It clearly differentiates this aggregate tool from siblings like get_gex, get_dex, and get_flow_levels by framing it as a combined bundle.

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 gives explicit guidance on choosing a view: pass view='gex', view='dex', view='oi', or omit it for the combined bundle. This provides clear context for invoking the tool, though it does not explicitly state when to prefer this bundle over individual sibling tools.

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