estimate_staking_yield

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

Annotations already indicate readOnly, destructive=false, idempotent, open world. The description adds that it uses current APRs, is forward-looking, returns specific fields (protocol, input amount, APR, projected rewards), and emphasizes no on-chain position reading. This adds significant behavioral context beyond 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 four sentences, all essential, with purpose upfront. No fluff or redundancy. It efficiently conveys purpose, usage context, output, and limitations.

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 tool is simple (2 params, query). Description mentions return values explicitly despite no output schema, and provides sufficient context with annotations covering safety and idempotency. It also informs about pairing with a sibling tool for actual holdings.

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?

The input schema has 100% coverage with detailed descriptions for both parameters (protocol enum and amount with examples). The description does not add new semantic information about parameters beyond what the schema provides, so baseline 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 projects annual yield on a hypothetical staking amount for Lido or EigenLayer using current APRs. It distinguishes itself from sibling tools by explicitly noting it is forward-looking and does not read on-chain positions, and recommends pairing with get_staking_positions for actual holdings.

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 specifies when to use: 'for 'what would I earn if I staked X ETH?' questions before the user commits capital.' It also clarifies what it does not do (no wallet reading) and suggests a complementary tool (get_staking_positions), giving clear boundaries.

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