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

Annotations declare readOnlyHint=true, and the description doesn't contradict this. It adds valuable behavioral context: the data is simulation-aware (not actual flow), the snapshot includes gamma flip/walls/pin score, hedge_flow is per-bar with cumulative totals, and the staleness issue for settled OI. These details go beyond the annotation without being redundant.

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 a single dense sentence that front-loads the core purpose and then systematically defines the three views. Every clause serves a purpose except the cryptic 'Growth+' at the end, which adds no functional information and slightly weakens conciseness. Overall, it's efficient and well-structured.

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 multi-view tool with no output schema, the description does a solid job: it explains what snapshot, series, and hedge_flow return and their intended use. It omits some edge-case details (e.g., exact data availability windows or error behavior), but the combination of schema coverage, readOnlyHint, and view descriptions makes it sufficiently complete for an agent to decide when and how to invoke it.

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 100%, so the schema already documents all parameters clearly. The description adds a little extra meaning by associating 'per bar' with hedge_flow and naming view-specific outputs (e.g., gamma flip, walls), but it doesn't materially deepen parameter understanding beyond the schema. Baseline 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 opens with 'LIVE simulation-aware 0DTE flow' and enumerates three specific views (snapshot, series, hedge_flow), each with concrete outputs. It explicitly contrasts with get_zero_dte, distinguishing itself as a fresher, simulation-based alternative. This gives a specific verb+resource and clear differentiation from siblings.

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 explicitly names get_zero_dte as an alternative and explains why this tool is preferred when live data is needed ('fresher than get_zero_dte which uses settled OI and goes stale after ~10:30 ET'). It also maps views to use cases (charting for series, hedging estimates for hedge_flow). However, it doesn't provide broader exclusions or comparisons to other flow-related siblings like get_flow_live or get_flow_signals.

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