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

With no annotations, the description carries the full burden, and it does disclose two non-obvious behaviors: a hard cap of 24 moments per call, and that every asset is read at each moment, so the call is a cross-product rather than a per-asset lookup. The point-in-time guarantee ("Everything reported was knowable at that moment") is a meaningful disclosure about lookahead bias. It loses a point for deferring the default values of window_minutes and after_minutes to "the same defaults the searches draw at" instead of stating them.

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 purpose, the routing rule, and the parameter meaning each arrive in that order, so the definition is well front-loaded. However, the closing sentence about defaults is both vague and unactionable, and the descriptive flourish about dollar, yields and oil is longer than the routing point requires.

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 no-annotation tool with no output schema, the description does well to name the reported fields (close, returns, window shape, after path) since nothing else explains the return values. The remaining gaps are material though: the asset universe being compared is never defined, and the defaults for the two optional parameters are handed off to unnamed "searches" rather than stated, leaving an agent unable to predict what a call without window_minutes actually reads.

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 all three parameters are already documented in the input schema, which sets the baseline at 3. The description does add genuine semantics the schema cannot express — that each moment is applied to every asset, making ago comparisons across both dimensions — but it still leaves the actual default integers for window_minutes and after_minutes unspecified, which is the one thing an agent cannot derive from the schema.

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 opening clause names a specific verb and scope (read every asset at a single moment, side by side) and then enumerates what is returned: close, day and three-day returns, the pre-move shape and the post path. It explicitly separates itself from get_market_state, so an agent can route between them without opening either 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?

Usage is stated positively ("when the question is about the surroundings of a moment rather than the one asset") with a concrete example, and negatively by naming the alternative and its condition ("For one asset at one moment in more detail, use get_market_state"). The exclusion is explicit rather than implied.

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