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

Annotations are absent, so the description has to carry the full behavioral burden. It does disclose payment/auth requirements and the max/default for `window`, which are genuinely important. But it doesn't explicitly say the operation is read-only, whether usage counts against rate limits, or how the data is aggregated, leaving a partially transparent picture.

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?

There is no wasted prose—every sentence carries information—but the lengthy payment/auth preface is placed before the main purpose, nearly hiding the core use case. Restructuring to state the market-data report first and then the auth/cost note would give better clarity and improve navigability.

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 the simple input schema and an existing output schema, the description largely supplies enough to call the tool, especially by doing parameter semantics and auth costs. However, the absence of any guidance on when to select this over a sibling market or MEV tools creates a material completeness gap for an agent's tool-selection decision.

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 schema provides only the property name `window` with no description, while the description says it is in hours, defaults to 24, and maxes at 720. That transforms a bare numeric field into a usable parameter, and coverage far beyond what the raw schema alone offers.

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 states the resource clearly: Ethereum block builder market over a window, including blocks delivered, value per relay, and top builders. It does not rely on a verb but the noun-phrase is descriptive enough to infer an analytic report, and it stands apart from the broader sibling list only by the mention of 'builder relays'.

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 covers authentication and payment requirements, plus valid values for `window`, but never says when to choose this tool over related siblings like `mev_intel` or `mev_bots`. There is no condition such as 'if you need builder-level relay breakdowns' or 'do not use this for mempool data', leaving selection to happen without guidance.

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