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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so safety is covered. The description does add real behavioral context beyond them: recording policy ('recorded every minute Kellian saw whole'), gap semantics ('a minute not recorded has no bar'), and the informational-only framing. However, it says nothing about limits, history depth, or window-size constraints, which matter for an open-world data pull.

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 verb and resource, then the payload, then the caveat. Three sentences with little waste, though the parenthetical about 'the underlying stock, index, commodity or coin price, recorded every minute Kellian saw whole' is dense and slightly awkward.

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?

An output schema exists, so return values need not be spelled out, yet the description still characterizes the bar shape and the sparse-data rule, which is the key correctness detail for interpreting results. Missing only window-size or history-depth expectations for an open-world time-series read.

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 75% (to, from, interval documented; symbol only has a pattern). The description adds 'bars for a window' and the inclusive/exclusive framing implicitly, but does not explain the symbol format, the interval options, or bar alignment beyond what the schema already states. Baseline 3 is appropriate when the schema does most of the work.

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?

States a specific verb and resource ('Read the Kellian Perps index ... as bars') and defines what that index actually is (the underlying stock/index/commodity/coin price), plus the bar payload (OHLC and minutes per bar). It never names a sibling it must be distinguished from (e.g. get_market_chart), so the differentiation is left implicit, but the resource is distinctive enough to identify.

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?

'Use it for the real range of a price market's window' gives an implied use case, and 'Information only' hints at the informational/non-trading scope. There is no explicit when-not-to-use or named alternative among the many sibling read tools, so the agent must infer the boundary.

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