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 non-obvious context: data is observed monthly since 1926, output is medians with 20th-80th percentile bands describing a matched sample, and explicitly that these are not forecasts or probabilities. That framing is exactly the kind of behavioral disclosure annotations cannot carry.

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?

It is dense but front-loaded, leading with the core analogue concept before parameter specifics, and almost every clause carries information. It runs long for a description and packs several semicolon-joined parameter notes that could be tightened, but there is little outright 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?

For an 11-parameter, zero-schema-coverage tool with an output schema present, the description supplies the semantics the schema lacks, warns that results are descriptive statistics rather than predictions, and instructs the agent to cite the page link. An agent has enough to call it correctly without opening the schema.

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?

With 0% schema description coverage, the description has to carry the load and does so for most parameters: allowed `window`/`horizon` values, `magnitude` units per asset class (percent, bp, VIX points) and null-for-direction, `conditions` syntax and the "none" sentinel, `cohort`, and `reference`. However `count`, `since`, `direction`, and `tolerance` are never explained, and the `asset` list is only partially enumerated ('and more').

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 states a specific operation on a specific resource: find historical analogues where an asset moved a certain way over `window` months and report what followed over the next `horizon` months. This is plainly distinct from every sibling (get_analyst, get_catalog, get_latest, search), all of which are data-retrieval tools rather than conditional historical analysis.

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 gives clear in-context usage: which values `asset` takes, how `conditions` defaults/clears/sets, and what `cohort` and `reference` do, plus a caveat about citing the page link. It never states when NOT to reach for this tool or which sibling to prefer for adjacent needs, so it stops short of full alternative routing.

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