Agent Zero — ERC-8004 Trust Filter

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

With no annotations, the description carries the full burden and does so: it discloses what is deliberately excluded (no owner identity string, no payment amounts), the error behavior ('Returns an `error` field if the agent is not indexed'), the `locked` map of nulls, the `unlock` block contents, and the free-vs-paid boundary. This is well beyond what the (absent) structured fields 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?

Front-loads the one-line purpose, then a labeled Args block, an Example, a Returns paragraph, and the paid counterpart. Length is justified by the absence of an output schema and parameter descriptions; no sentence is filler — even the 'no owner identity / no payment amounts' line earns its place by preventing wrong expectations.

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 free-scope read tool with no output schema and 0% schema coverage, the description supplies everything needed: parameter semantics, default behavior with no arguments, the return field set, the error case, and the paid upsell with exact endpoint and price discovery. Nothing an agent needs to call it correctly or interpret the response is missing.

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 0%, so the description must compensate entirely — and it does. It documents both params as optional, the chain enum values ('base', 'ethereum'), the default chain, the numeric meaning and default of agent_id (19353 / Agent Zero), and gives a concrete call example showing the empty-object form.

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's opening line states a precise verb+resource: objective, counts-only signals for one ERC-8004 agent. It enumerates the exact signals returned (reachability, TLS validity, x402 support, MCP tool count, etc.), so an agent knows exactly what it gets. It stops short of naming or contrasting the sibling tools (get_coverage_stats, get_leaderboards, get_network_teaser), which keeps it from a full 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?

Explicitly states the decision context: 'Use this to vet a counterparty agent before transacting.' It also names the alternative and the condition that selects it — the paid counterpart endpoint is called out as the source of decision-driving values (trust_verdict, readiness_score) this free response returns as null. When-to-use and when-to-step-up are both covered.

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?

Since there are no annotations, the description must carry the full burden. It discloses that the tool is read-only (returns data) and details what is NOT included (e.g., no names/addresses), which is useful. It also mentions a unique behavior: every response includes an 'unlock' block with pricing info for a paid endpoint, which is helpful. It doesn't specify rate limits or error cases, but for a no-parameter read tool, this is sufficient.

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 description is moderately concise with two paragraphs. The first paragraph states the primary function and output format, which is good front-loading. The second adds the paid counterpart and unlock block, which is useful but slightly verbose. Each sentence contributes value, though the second paragraph could be tightened without losing key info. It is structured but not overly long.

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?

Given the tool has no parameters, no output schema, and no annotations, the description is complete enough for an agent to call it correctly. It explains what to expect in the response (counts, per-chain breakdown) and the paid upgrade. There is no missing information that would prevent correct usage.

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 zero parameters and 100% schema coverage, the schema itself doesn't provide any parameter details. The description compensates by explaining the type of data returned (counts, breakdowns, per-chain) and the additional unlock block. This is valid because the tool takes no arguments, so the description effectively clarifies what the tool provides given no inputs.

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 clearly states the tool's purpose: 'Live coverage of the ERC-8004 agent economy' with specific output details. It distinguishes itself by emphasizing it returns counts only, not actual names or addresses, which differentiates it from siblings like get_agent_summary. The verb 'get' and the resource 'coverage stats' are explicit and precise.

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 description provides clear guidance on when to use this tool: to 'size the market' and see where capability density is growing. It also mentions a paid counterpart for more detailed data for those needing capability-level specifics. However, it does not explicitly state when NOT to use this tool or mention alternatives like get_agent_summary, though the definition implies the free/paid distinction.

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?

There are no annotations, so the description carries the full burden. It discloses exactly what fields are returned (agent_id, chain, public name, shareable URL, relevant count), what is excluded (owner wallets, handles, endpoint URLs), and that every response includes an 'unlock' block with paid endpoint/price/payment discovery. Minor omissions like pagination or rate limits are not critical for a no-parameter read-only tool.

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 description is dense but every sentence adds value: it fronts the main purpose, then details the lists, then gives usage guidance and notes the paid alternative. No filler or redundancy.

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 and no annotations, the description fully explains what the response contains, what it omits, and the response's unlock block. For a zero-argument tool, this is sufficient for correct invocation and interpretation.

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 tool has 0 parameters, so there is nothing to clarify. Baseline for 0 params is 4; the description adds no unnecessary parameter commentary, which is appropriate.

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 ('leaderboards' of ERC-8004 agents) and a clear action (returns three ranked lists). It details exactly what the lists rank (live MCP tool count, OpenAPI method count, most-recently indexed), which distinguishes it from sibling tools like get_coverage_stats or get_agent_summary.

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?

Explicitly says 'Use this to find the most capable / most active agents to integrate or watch.' It also names a paid alternative (GET /v1/intel/trending) and explains what that returns, giving the agent both a when-to-use and a when-not-to-use reference.

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 present, the description carries the full burden of explaining behavior. It does so well: it discloses the ≤200-node cap, truncation, free-to-paid distinction, and the `unlock` block in every response. It stops short of stating read-only safety or response format details, but the core behavioral traits are visible.

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 description is organized into three tight sections: what the result is, how to use it, and the paid upgrade path. Every sentence adds useful information, and the key cap/truncation facts are front-loaded in the first lines.

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 parameterless read tool, the description is complete: it defines the returned nodes/edges, the cap, the relationship to the paid full graph, and the unlock mechanism. There is no output schema, so the prose adequately covers what an agent would need to decide to call it.

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 tool has 0 parameters, so there is nothing for the description to explain. Per the baseline rule, 0 params receives a 4; the description gives no parameter information, but none is needed.

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 resource ('on-chain agent-to-agent payment graph') and a concrete behavior: 'Returns connected agents (nodes) and the value flowing between them (edges), capped to a small connected sample (≤200 nodes).' This is unambiguous and clearly distinct from sibling tools like get_agent_summary or get_leaderboards, which cover different data. The 'Use it to see who pays whom' line reinforces intent.

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 explicitly tells agents when to use this tool: as a truncated preview to see who pays whom, and names the paid alternative `GET /v1/intel/graph` for when the full network is needed. The condition (needing every node and edge without a cap) is stated directly, so an agent can route to the right tool without guessing.

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