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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new context: history depth since 2015, clipping to as_of to prevent look-ahead, and that free keys are limited to daily bars over the last 12 months. That entitlement disclosure is exactly the kind of thing annotations cannot express.

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 tight sentences that front-load the resource and data shape, then interval, then temporal clipping, then tier limits. No filler, though the order puts a breadth statement ('and more') slightly ahead of the more actionable constraints.

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 5-parameter tool with no output schema, stating the OHLCV shape is a solid substitute. Still missing: row-count or pagination behavior, start/end semantics and their default range, and what an empty or tier-blocked response looks like — all relevant for a tool an agent will call repeatedly.

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 40% schema coverage, the description meaningfully supplements interval (enum values plus default) and reinforces as_of clipping, and gives a symbol format example. However, start and end — the two undocumented parameters — receive no explanation of format, defaults, or interaction with as_of, leaving the coverage gap partly unaddressed.

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?

Opens with a specific verb+resource ('OHLCV bars for crypto pairs') and scopes the asset class with concrete examples and a start year. It never names the adjacent get_bars (equities) sibling, so an agent must infer the crypto-vs-equity split from the name alone.

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 does give practical selection guidance for the interval parameter (four valid values, 1day is the default) and states a tier-based constraint, which implicitly tells the agent when results will be limited. There is no explicit when-to-use/when-not framing and no pointer to get_bars or other siblings for non-crypto data.

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