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

Annotations already declare readOnlyHint and destructiveHint, and the description adds context by explaining the data sources (live relay acceptance rate and submission volume) and that it returns only the top recommendation. It also mentions a paid endpoint for full telemetry, which is useful 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?

Two sentences, front-loaded with the core purpose and outcome. The second sentence efficiently introduces the extended resource and payment requirement without unnecessary detail.

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?

For a simple read-only tool with no output schema, the description is complete: it explains the recommendation criteria, the returned data (builder name and acceptance percentage), and a pointer to the full ranked list. No key information is missing for an AI agent to use this tool effectively.

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?

With zero parameters, the description fully compensates by explaining what the tool does and what it returns. There is no need for parameter-level semantics, and the description provides enough detail about outputs and criteria.

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 a specific action: getting the best Ethereum block builder for MEV bundle submission right now, based on live relay acceptance rate and submission volume. It distinguishes from siblings like recommend_bundle_submission by focusing on builder selection, and specifies the return value (builder name and acceptance percentage).

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?

Provides clear context: use this when you need the best builder immediately based on live telemetry. It also points to an alternative endpoint for the full ranked list with payment, but does not explicitly exclude or contrast with sibling tools such as recommend_bundle_submission.

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