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.