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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial extra context: the render uses the same geometry as the screen, the envelope cone appears only when calibration permits, output is PNG plus JSON, windows must be in the past, and there is a 600-bar cap. These are real behavioral traits beyond the structured fields.

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, front-loaded with the core purpose, and every sentence carries information (what is rendered, how to treat the outputs, the limits). The middle sentences are dense but not redundant; no 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?

With no output schema, the description correctly takes on the burden of explaining returns — it specifies a PNG plus chart_state JSON and warns how to interpret each. It also covers the window and bar-count constraints, so an agent has everything needed to call it correctly.

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%, so the baseline is 3, but the description adds meaning the schema lacks — a 600-bar ceiling on the from/to window, the 'past windows only' constraint, and the note that the indicators selection controls whether the envelope cone is drawn. That extra semantics lifts it above the baseline.

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 a specific verb (server-side render) and resource (a chart plate for one market/timeframe/window), and names exactly what is produced: a PNG plus the chart_state JSON. It implicitly differentiates itself from the chart_state sibling by declaring it returns both the picture and that JSON, so the agent knows what it is getting without opening a schema.

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?

Gives clear usage context and constraints — 'Past windows only; at most 600 bars' and the rule to quote numbers from the JSON rather than the image. It does not explicitly say when to prefer chart_state or the image sibling over this tool, so there is no full when/when-not routing, but the operating conditions are well stated.

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