Ethos

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.

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered; the description still adds real value with cost/auth ('Free, no payment or key; the same answer as the free Ethos API') and pagination behavior. It also discloses the returned fields and an example payload, which is well beyond what the annotations provide.

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?

The purpose is front-loaded in sentence one and the routing advice follows logically, but the definition carries a bulky inline example output payload that dominates its length. Since no output schema exists the example has value, yet the full JSON blob is heavier than needed to convey the return shape.

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?

There is no output schema, and the description compensates by enumerating returned fields (credibility score, status, linked wallets, social accounts) and showing a concrete response with total/limit/offset. Combined with the free/no-key note, an agent has everything needed to call this correctly for a 3-parameter read tool.

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 query, limit and offset are already documented, and the baseline is 3. The description reinforces the accepted fragment types (name, partial handle, part of an address) but adds no syntax, matching rules, or paging semantics beyond what the schema states.

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 first sentence names a specific verb (find/search) and resource (person or project on Ethos) and states the discriminating input condition: 'when you only have a name, a partial handle or part of an address'. That condition implicitly but effectively separates it from the identifier-exact siblings ethos_user_by_address and ethos_user_by_x.

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?

It gives an explicit workflow trigger ('The starting point when a user asks about someone by name: search, pick the match, then score or profile it by userkey') and a secondary use case (disambiguating impersonators). It stops short of naming sibling tools or stating when NOT to use it, e.g. when an exact address or X handle is already known.

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

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, and the description still adds meaningful context: it is free with no payment or key, and returns the same answer as the free Ethos API. That cost/auth disclosure is the kind of detail annotations cannot express. It does not discuss rate limits, caching, or behavior for an address with no profile.

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?

The core purpose is front-loaded as a question, followed by field inventory, use cases, cost profile, and examples in a logical order. It is dense rather than wasteful, though the long inline example output could be trimmed without losing meaning.

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?

There is no output schema, so the description's example output with real field names (profileId, displayName, score, status, userkeys, xpTotal, influenceFactor, stats) is essential and supplied. Combined with cost and use-case guidance, an agent has everything needed to call and interpret this single-parameter tool.

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 the regex already constrains format, so the baseline is 3; the description adds value by showing a concrete example address and tying the parameter to the profile that holds it. Marginal gain is limited because the schema already documents the parameter type and pattern.

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 opens with a specific question ("Who owns this wallet, and what is their reputation?") and then names the exact resource: the Ethos profile holding an EVM address, with the fields returned. An agent can tell this is a per-address profile lookup, distinct from the search/score/x-handle siblings. It does not explicitly name ethos_user_by_x as the alternative for handle-based lookup, which keeps it below 5.

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?

Concrete when-to-use cases are given: attaching a name and trust level to a counterparty before a trade, transfer, airdrop, or allowlist decision, and screening addresses for bad actors. No explicit when-not or named alternative is provided, so the sibling routing is only implied by the input being an address.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description's value-add is the cost/auth disclosure: 'Free, no payment or key; the same answer as the free Ethos API.' That removes a real planning question for the agent. It adds no notes on rate limits or what happens for a nonexistent handle, which keeps it below a 5.

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 the core question and resource, then field list, then use cases, then a worked example. The example output blob is long, but it is doing load-bearing work because no output schema exists. Slightly dense prose (the field enumeration runs long) keeps it from a 5.

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?

There is no output schema, and the description compensates fully by showing the complete response shape including nested stats, userkeys format, and field types. Combined with cost/auth disclosure and a sample input, an agent has everything needed to call this single-parameter tool correctly on the first attempt.

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 the schema already explains 'X handle without the @, or the numeric X account id', so the baseline is 3. The description adds a concrete worked input, {"handle":"ethos_network"}, which adds real value by demonstrating the no-@ convention and confirming the parameter key name in practice.

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 opens with a specific question-form verb phrase and then names the exact resource: 'The Ethos profile for a handle or numeric account id', followed by an enumeration of the fields returned (display name, credibility score/status, wallets, socials, XP, influence factor, review/vouch counts). That input shape ('handle or numeric account id') implicitly separates it from ethos_user_by_address and ethos_search_users.

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?

Three concrete usage contexts are given: vetting an account before engaging, resolving a handle to its wallets, and enriching a mention with reputation. What is missing is explicit routing — it never names ethos_user_by_address as the alternative when you have a wallet instead of a handle, nor ethos_score when only a score is needed, so the agent must infer the boundary.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile needs no restating. The description adds value beyond them: XP sources (reviews, vouches, invitations), the fact it is free with no payment or key and matches the public Ethos API, and a sample scalar output. Missing only things like rate limits or caching/staleness behavior.

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 the practical question the tool answers, then scope, then the pairing advice and a compact input/output example. The opening rhetorical question and the 'long-standing vs fresh or dormant' clause are slightly padded, but no sentence is wasted overall.

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 single-parameter read tool with no output schema, the description covers what is returned (a total XP number, shown by example), the data source, the cost, and the natural companion metric. There is no output schema to defer to, and the example output fills that gap adequately.

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 the schema already enumerates every accepted userkey form (address, profileId, service:x.com, Discord, Telegram), so the description largely echoes it. The concrete example input {"userkey":"profileId:1"} adds a small amount of usable guidance but nothing about resolution ambiguity or invalid-key behavior.

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?

States a specific verb and resource: "Total XP earned across all seasons for a userkey," and immediately frames it as a history/activity measure as opposed to the credibility score, which lets an agent separate it from ethos_score and the user-lookup siblings without opening a schema.

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?

Gives clear when-to-use framing ("How active and invested is this person..." and "Use it alongside the credibility score to weigh how much history stands behind a reputation"), which routes the agent toward pairing it with ethos_score. It stops short of naming explicit exclusions or saying which sibling to call for the lookup portion instead.

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