arc_agents_stats

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Facts only — the concentration numbers are stated so you can draw your own conclusion,' which clarifies that the tool returns raw metrics without interpretation or bias. However, it does not disclose potential limitations like whether the numbers are approximate, cached, or how recent the data is. For a read-only stats tool, this is acceptable but not comprehensive.

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 a single, well-structured sentence that front-loads the tool's purpose and lists all metrics in a compact list. It avoids filler and each phrase adds meaningful content. It could be slightly shorter by dropping the 'Facts only' clause, but that clause provides a behavioral note, so it earns its place.

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 there is no output schema, the description must convey what the response looks like. It enumerates the categories of data but not the exact structure (e.g., field names, whether it's a flat object or nested, types). For a stats tool with zero parameters, this is a notable gap because the agent cannot predict the response format precisely. It is sufficient for basic understanding but not complete for reliable invocation without additional assumptions.

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 zero parameters, and the schema reflects this with an empty properties object. Per the rubric, a zero-parameter tool gets a baseline of 4 because there is nothing for the description to clarify about parameters. The description adds no param-related info, but that is not 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 verb and resource: 'Shape of Arc's ERC-8004 agent registry in one call,' and enumerates the exact metrics returned (total ids, distinct owners, distinct hosts, resolution counts, x402 vs payment declarations, status counts, concentration shares). This clearly distinguishes it from sibling tools like arc_agents_list or arc_agent_get, which return individual records rather than aggregate statistics.

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 implies usage is for obtaining aggregate registry statistics in a single call, but it never explicitly contrasts with siblings or states when NOT to use it. For example, it doesn't say 'for per-agent details, use arc_agent_get' or 'for list view, use arc_agents_list.' The context signals make it evident it's a stats tool, but the description leaves the routing to inference.

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