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

Annotations already declare readOnly, idempotent, non-destructive and open-world behavior, so the safety profile needs no restatement. The description adds genuinely useful non-annotation context: the call is free with no payment or key required, and it returns the same answer as the free Ethos API, which matters for cost/auth decisions and for deciding whether a failed call is worth retrying elsewhere. It adds nothing about latency, rate limits, or what happens for unknown/unscored keys, so it is solid but not rich.

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 front-loaded with the decision the agent actually faces ("Is this wallet, X account or person trustworthy?") followed immediately by the output definition and then use cases and input formats. It is longer than typical but nearly every clause carries information; the score range and example I/O are load-bearing, though the format list partly duplicates the schema.

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 carries the return contract itself and does so completely: score range (0-2800), the categorical level, and a concrete example output. Combined with accepted input formats and the free/no-key note, an agent has everything needed to call this and interpret the result.

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 description coverage is 100%, so the supported userkey formats are already documented, making the baseline 3. The description goes slightly beyond by listing the accepted identifier families again and supplying a concrete example input ({"userkey":"service:x.com:username:ethos_network"}), which removes ambiguity about how to assemble a handle-based key.

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 a specific resource and output precisely: an Ethos credibility score (0-2800) plus a level from untrusted to renowned, derived from named sources (peer reviews, ETH-backed vouches, slashes, linked history). What it does not do is explicitly differentiate itself from the sibling lookups (ethos_user_by_address, ethos_user_by_x, ethos_search_users), leaving the agent to infer that those return identity records while this returns a reputation score.

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?

Usage context is concrete and actionable: before trading with, following, quoting or paying an unknown counterparty, for ranking accounts by reputation, and for flagging scams and bots. That is strong when-to-use guidance, but no when-not conditions and no sibling alternatives are named, so it stops short of full routing guidance.

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