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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so safety is well covered. The description does add real behavioral context beyond them: results are assembled from multiple registries (reference and backing) and one facet is conditional on the address being a cell account. It stops short of stating what happens for unknown addresses, unregistered addresses, or non-EVM input, which matters for an open-world resolver.

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?

It is a single sentence with no filler, which is appropriately sized. But the structure is a dense colon-list of five ERC identifiers, front-loaded with an abstract noun phrase rather than the action, making it slower to parse than it needs to be.

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?

An output schema exists, so the facet list need not be re-explained and return values are documented elsewhere; the schema constrains the single input. What is missing relative to the tool's complexity is disambiguation from the single-facet siblings and any statement about behavior on unresolved addresses. Adequate but with clear gaps.

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 one parameter and 0% schema description coverage, the schema carries only a regex pattern (0x + 40 hex). The description mentions 'an address' and ties it to identity facets, which implies an EVM account address and connects the argument to the resolution semantics. It never states the accepted address forms or that the regex enforces EVM format, so the compensation is partial.

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 sentence enumerates the facets returned (ERC-8004 agent, ERC-8434 registry state, ERC-8444 record, KYA level, ERC-8468 cell status), so the resource is identifiable as a consolidated identity record for an EVM address. However, it is a noun phrase rather than a verb+resource statement, and the phrase 'ten-ERC view' does not match the five standards actually listed, which leaves the scope of the resolution ambiguous. It also never states what the returned object is (a merged record vs. multiple records) or that resolution is read-only lookup.

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?

There is no when-to-use guidance at all. The sibling list contains kya_check, cell_status, and world_describe, which appear to cover a subset of what this tool aggregates, yet the description gives no routing rule such as 'use this for a full profile, use kya_check for just the KYA level'. The conditional clause 'when the address is a cell account' hints at behavior but is not framed as usage guidance.

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