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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds behavioral details beyond annotations: it reads from the chain at past blocks, includes oracle prices, changes, and largest drawdown, and notes the history start point. No contradictions with annotations.

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 description is three sentences, front-loaded with the core data returned, then adds history start and a usage note. It is efficient with no redundant phrasing, though the second sentence about history start could be integrated more tightly. Still, it is concise and well-structured.

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?

The description covers the returned data (NAV, oracle prices, changes, drawdown), the historical scope (since deployment), and a clear use case. An output schema exists, so return format is likely covered. Minor omission: no mention of pagination or limit behavior, but that is in the schema. Overall complete for a read-only historical tool.

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%, with both parameters (points and interval) having clear descriptions and defaults. The description does not add extra parameter-specific details but provides context about the data returned. Since the schema already documents parameters, the baseline of 3 is appropriate.

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 description clearly states the tool returns NAV per GBLIN share over time, along with ETH/USD and BTC/USD oracle prices, changes, and drawdown. It specifies the resource (NAV history) and the verb (read), making it distinct from siblings like treasury.state or treasury.quote, which focus on current values.

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?

The description provides an explicit use case: 'Use it to judge how the index behaved against holding ETH or BTC over the same span.' This gives clear context for when to call the tool, though it does not mention alternatives or explicitly state when not to use it. The context of 'history' and 'over time' implicitly separates it from current-state tools.

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