get_indicator_graphics

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

With no annotations, the description carries the behavioral burden and it provides useful details: most recent primitives first, and extrapolated times flagged timeEstimated. These are real behavioral traits beyond the basic 'get' semantics, though it doesn't discuss errors or response shape.

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?

Three sentences, each carrying distinct value: what it returns, when to use it, and ordering/flag behavior. No filler or repetition, and the most important information is front-loaded.

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 simple read tool with three optional, fully-described parameters, the description covers the key context: primitive kinds, use case for drawing-only indicators, ordering, and extrapolation flagging. Without an output schema it could specify return structure more, but the given detail is sufficient for correct 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 description coverage is 100%, and each parameter already has a clear description including defaults and constraints. The tool description adds only redundant ordering context already present in limit_per_kind, so it provides no meaningful additional parameter semantics.

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?

States exactly what it does: retrieves drawing primitives (labels, trend lines, boxes/zones) from a Pine indicator on a TradingView chart. It also differentiates itself from numeric-plot tools by calling out drawing-only indicators, which clearly separates it from siblings like get_indicator_values.

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?

Explicitly says this is how to read drawing-only indicators with no numeric plots, giving clear context for when to use it. It does not explicitly name alternative tools for numeric plots, but the contrast with 'no numeric plots' implies the boundary well enough.

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