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

Annotations already mark this as read-only and open-world, and the description adds meaningful behavioral context: it is a projection rather than a guarantee, it annualizes the latest realized per-epoch rate using ~104.29 epochs/year, and it can return found=false for uncached providers. These details go well beyond the annotations without contradicting them.

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?

Four dense sentences, each earning its place: what it does, how it annualizes, what it returns, and its caveats. The most defining constraints are front-loaded, and there is no 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?

Given there is no output schema, the description appropriately explains the return values (APR, annual/monthly reward in FLR) and the found=false fallback. It also covers limitations and scope. Minor gaps remain around precise input-unit clarification and provider_address validation semantics, but overall it is sufficient for correct invocation.

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 0%, so the description must compensate. It conveys the general semantics of 'an amount' and a 'provider' with a default of FlareWatch, but it doesn't explicitly tie these to the parameter names amount_flr and provider_address, nor does it clearly state the input unit for amount_flr or the provider address format. This is adequate but leaves the agent to infer some parameter details.

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 uses a specific verb ('Estimate') and resource ('annual WFLR FTSO-delegation rewards'), and immediately distinguishes this from actual reward history and P-chain staking. It clearly positions the tool as a projection, which separates it from the sibling read/history tools.

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 gives clear context: this is for simulating/a projecting FTSO delegation rewards, not P-chain staking, and it notes what happens when the provider isn't cached (found=false). However, it doesn't explicitly name alternative tools for actual rewards or historical metrics, leaving some routing to inference.

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