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

Goes far beyond the readOnly/openWorld annotations: discloses pricing ($0.002/call, x402, USDC on Base, Base-only for MCP), that found:false is still billed while bad input/RPC failure may not be, that returned names are untrusted third-party data, and that reverse results are forward-verified with a true/false flag. None of this is derivable from annotations or schema.

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?

Front-loaded with purpose and mode, then billing and trust caveats in descending importance. The style is telegraphic sentence fragments and the ordering is dense, but nearly every clause (billing, CCIP-Read exclusion, untrusted data) carries decision-relevant information.

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?

With no output schema, the description correctly explains what comes back: address/resolver/registry forward, verified primary names reverse. Also covers cost and failure billing, which an agent must know before paying. Minor gap: behavior when both name and address are supplied is left unspecified.

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 coverage is 100% and both properties already carry descriptions including the same "Give name or address" phrasing, so the description adds little parameter-level meaning. The forward/reverse outcome mapping is useful but sits closer to return-value semantics than parameter semantics.

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?

Names the specific resource (ENS and Basenames) and both verbs of operation (name→address forward, address→primary name reverse), with concrete examples (vitalik.eth, jesse.base.eth). No sibling tool in the list does naming resolution, so it is unambiguously distinguishable.

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?

"Give name or address" plus the forward/reverse split tells the agent which parameter selects which mode, and the explicit exclusion of off-chain/wildcard (CCIP-Read) names prevents a class of futile calls. It stops short of stating when to prefer this over an alternative path (e.g. caching via other tools), but no true sibling alternative exists.

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