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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so safety is covered; the description then adds real value the annotations do not: a cost signal ($0.02), the 15-minute measurement window, the full set of data sources consulted, and the return shape (drivers with direction and weight plus a one-sentence summary). It stops short of stating auth requirements or rate limits, but goes well beyond the structured hints.

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?

Front-loaded with the core question, then cost, then scope and output. Two sentences with no filler; the parenthetical source list is dense but earns its place by telling the agent exactly what evidence the answer synthesizes.

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 takes on the burden of describing the return and does so (drivers with direction/weight plus a one-sentence summary), and it scopes time window and asset classes. An agent has enough to call it correctly; only cross-tool routing and any auth/cost caveats beyond price are left implicit.

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?

Only one parameter (symbol) with 100% schema description coverage and inline examples (ETHUSD, NVDA, TSLA), so the schema already carries the semantics. The description adds the universe of supported symbol types, but no format or normalization detail beyond the schema; baseline 3 applies.

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?

Specific verb+resource: it explains the 15-minute price move for a symbol via enumerated drivers (on-chain flow, unusual activity, smart money, perp crowding, news, filings, insiders). The causal framing clearly distinguishes it from snapshot/summary siblings, though it never names those alternatives.

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 implied by the opening question ('Why is a symbol moving?') and the stated asset-class coverage (crypto, tokenized stocks, US stocks), which helps scoping. However there is no explicit when-to-use vs when-not, and no mention of sibling tools like market.snapshot or market.summary that an agent would need to disambiguate.

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