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

With no annotations, the description carries the full burden, and it does disclose the response payload categories, which is genuinely useful. It does not state that the operation is read-only (only implied by 'Get'), nor what happens for an unknown address, whether lookups are rate-limited or permissioned, or whether both parameters can be passed together — meaningful gaps for a lookup tool with zero annotation coverage.

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?

Three short sentences: purpose, return contents, then the addressing hint and sibling alternative. The most decision-relevant information is front-loaded and nothing is redundant or padded.

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?

No output schema exists, and the description compensates by listing the returned data categories, so an agent can reason about results. The remaining hole is parameter behavior (address vs identifier, both/neither cases) plus any precondition or failure-mode context, which keeps it from being fully complete.

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 0% and neither parameter has a description, so the description must compensate; it does partially by naming both inputs and giving a format hint for 'address' (0x...). It never explains what an 'identifier' is, how it differs from an address, or the precedence when both are supplied, leaving half the parameter surface underspecified.

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 ('Get account information') and enumerates the returned payload (account details, relationships/claims, financial positions, associated atoms), so the agent knows exactly what the tool produces. It also names a sibling, search_atoms, and the condition under which that sibling is preferred, which separates it from the other account-oriented tools in the list.

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 a clear usage hint ('Works best with wallet addresses (0x...)') and an explicit alternative for ENS data ('search_atoms provides richer relationship discovery'). It stops short of saying when to use 'identifier' instead of 'address' or what happens when both/neither are supplied, so the guidance is strong but not exhaustive.

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?

With no annotations, the description carries the full behavioral burden. It discloses that the response includes nested activities and connections, which is useful, but says nothing about result size, pagination, depth limits, or cost of traversing a graph — all material for a potentially heavy read operation.

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 compact sentences with the core action front-loaded and no filler. There is mild redundancy between 'relationships/interactions' and 'activities and connections', but it costs little.

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 two-parameter read tool with no annotations and no output schema, the description covers what the tool does and roughly what it returns. It falls short on operational detail — pagination, volume, or what 'connections' actually contains — which an agent would need before calling it on a large account.

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%, so both account_id and predicate are already documented with examples in the schema. The description adds no meaning beyond that baseline and never explains what filtering by predicate does to the returned follower set.

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 verb and resource ('Get followers of an address') and adds what comes back ('follower accounts with their activities and connections'). It is clearly distinguishable from the inverse sibling get_following by name, though it never explicitly contrasts itself with it.

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?

The closing phrase 'for social network analysis' implies a use context, but there is no explicit when-to-use, when-not-to-use, or named alternative such as get_following or get_account_info. The agent must infer selection from the tool names alone.

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?

No annotations are supplied, so the description carries the full disclosure burden, and it does state what comes back: followed accounts plus their activities and connections. It says nothing about result volume, pagination, ordering, or whether the traversal is bounded, which matters for a graph-expansion call that can return large payloads.

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 with the core operation front-loaded and no filler. The second sentence is somewhat redundant with the first, restating the return content in slightly different terms, but it is not wasteful enough to hurt.

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 annotations and no output schema, the description does the minimum needed to explain the result shape and its analysis purpose. It leaves out practical call details such as result size behavior and whether connections are expanded recursively, which an agent would want before invoking a graph query.

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 both account_id and predicate are already documented with examples, making 3 the baseline. The description adds no meaning beyond the schema and notably never mentions the predicate filter, which is the only parameter whose effect is non-obvious.

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 verb and resource: 'Get accounts that a given address is following,' which reads as the mirror of the sibling get_followers. It adds scope detail ('their relationships') but never explicitly names get_followers or any sibling as the contrasting choice, so differentiation is implied by wording rather than stated.

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 is only implied through the phrase 'for social graph analysis,' which gives a loose context but no explicit when-to-use or when-not-to-use conditions. It never tells the agent to prefer get_followers for the inverse direction or another sibling for plain account lookups.

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?

With no annotations, the description carries the full burden and does state the core behavior: it resolves an identifier to a wallet address. It leaves important traits unstated, though: whether the lookup is an exact resolve or a fuzzy search (the word 'search' suggests one thing, 'for the given identifier' another), what happens when nothing matches, and whether ENS resolution involves network calls or latency.

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 short sentences with the purpose front-loaded and no filler. The second sentence partly restates the first's implication, but the definition is still well within an appropriate size.

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 lookup with a fully described schema and no output schema, stating the return value covers a lot. It still omits not-found behavior and match semantics, which are exactly the details an agent needs before calling a 'search' tool that returns a single address.

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%, and the schema already says the identifier is 'typically an ens address' with an example, so the baseline of 3 applies. The description adds no format, normalization, or matching semantics beyond what the schema field documents.

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?

It states a concrete verb and resource ('Search for account addresses by ENS name or identifier') and the return ('wallet address'), so the agent knows exactly what the tool produces. It falls short of a 5 because it never differentiates itself from the sibling get_account_info, which an agent could plausibly pick for the same account 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?

The input domain ('ENS name or identifier') implies when the tool applies, which is the definition of implied usage. It never says when to prefer this over get_account_info or search_atoms, and gives no exclusions or prerequisites, so routing between siblings is left to guesswork.

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?

With no annotations, the description carries the full disclosure burden. It does usefully preview the return payload (entity info, as_subject_triples relationship data, financial fields like market cap and shares), but says nothing about result limits, ordering, pagination, or whether a multi-query request merges or keeps separate result sets.

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?

Four compact sentences, front-loaded with what is searched, then what is returned, then when it shines. The as_subject_triples parenthetical and financial-field list are dense but each earns its place by telling the agent what it will get back.

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 search tool with no annotations and no output schema, the description does a reasonable job on the return side but leaves the input contract unexplained. An agent knows what to expect back but not how to shape a multi-query request or interpret its results.

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?

The single parameter `queries` has 0% schema coverage — no description, no item semantics — and the description never mentions it. The agent cannot tell from either source that the input is an array of search strings, how multiple queries are combined, or how results map back to each query.

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 gives a specific verb (search) and names the resource types covered (accounts, things, people, concepts) plus the matchable fields (name, description, URL, ENS domain). It is clearly a broad entity search, which implicitly separates it from narrower siblings like search_account_ids and search_lists, though it never names them explicitly.

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 offers positive usage signals — 'Excellent for ENS names, discovering social connections, and semantic relationships' — which tell the agent what this tool is good at. It stops short of explicit when-not guidance or pointing to any of the five sibling tools as an alternative.

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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that results contain lists with items and are sorted by relevance, but omits permissions, pagination, result limits, and empty-result 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?

Two short sentences, front-loaded with the purpose and followed by return behavior. Every sentence carries useful information and there is no filler.

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 one-parameter search tool this covers the basic purpose and return ordering. However, with no output schema, it should say more about result shape, pagination, and limits to be fully self-sufficient.

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?

The single query parameter is fully documented in the schema, so the baseline is 3. The description adds slight nuance by saying matching is by name or topic rather than only schema wording 'object label', but it does not explain matching semantics such as exact vs fuzzy search.

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 verb ('search') and resource ('curated lists of entities'), including that matching is by name or topic. This is clear enough to separate it from sibling search tools like search_atoms, though it never explicitly contrasts with them.

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 implies usage by saying lists can be searched by name or topic, but gives no explicit guidance on when to choose this tool over search_atoms or search_account_ids. There are no exclusions, prerequisites, or alternative-routing instructions.

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