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

With no annotations provided, the description carries the full burden and does add substantive behavior: it defines the size buckets and interprets divergence. It does not disclose the exact delta computation or windowing behavior, but the provided definitions and signal interpretation go meaningfully beyond the bare tool name.

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?

Two tight sentences with no filler. The core metric and thresholds are front-loaded, and the signal interpretation is a single clause at the end.

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 metric and its segmentation are well explained, but with no output schema and no parameter guidance, the return format and the effect of the minutes parameter remain unstated. It works as an overview but not as complete call-time guidance.

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 0% and the description does not mention symbol or minutes at all. The agent must infer their meaning from names and defaults; the size-bucket definitions do not clarify what time window 'minutes' controls or accepted symbol formats.

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 states a specific metric (cumulative volume delta) and its segmentation by trade size with exact thresholds (retail <$10K, mid <$100K, large <$1M, whale >$1M). It also adds an interpretive signal (whale-vs-retail divergence = smart-money signal), which clearly distinguishes it from sibling analytics tools.

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 implies a use case by framing whale-vs-retail divergence as a smart-money signal, but it never states when to prefer get_cvd over siblings such as get_microstructure or get_footprint, nor does it give explicit exclusions or alternatives.

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