token_graph

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

Annotations declare readOnlyHint=true and destructiveHint=false, so the tool is known safe. The description adds behavioral context beyond annotations by specifying the kind of insights returned (edges with strength/confidence, cluster membership, wash-trading detection), which helps the agent set expectations about the output. It does not contradict annotations. The description carries the burden for non-safety behaviors and does so adequately.

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 concise and well-structured: it front-loads the cost, then the main purpose, followed by the key outputs and a usage note. Every sentence contributes information, and the differentiation from token_wallets is integrated naturally. There is no wasted wording.

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?

The tool has one required parameter with schema coverage, an output schema, and a description that explains the main purpose and usage context. The description mentions the nature of the output (edge strength, clusters, wash-trading), which is informative. While it doesn't detail every aspect of the returned graph, the output schema covers the structure. It is complete enough for an agent to decide when to call it, though it could explicitly state that it is complementary to token_wallets and perhaps other network-related tools. Still, it meets most criteria for completeness.

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% as the sole required parameter 'mint' has a description ('Solana token mint, base58.'). The tool description adds no additional parameter-level semantics beyond the schema, but with full coverage, the baseline score of 3 is appropriate. The description mentions 'token' in general context, but the schema already defines the parameter clearly.

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 explicitly states the tool's purpose: 'The wallet relationship graph behind a token' with specific entities (edges, strength, confidence, clusters, roles, wash-trading wallets). It also differentiates from a sibling tool: 'token_wallets names the holders; this shows how they are CONNECTED and whether a distributed-looking set is one person.' This gives a precise verb-resource and distinguishes it from the most closely related tool.

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 context for when to use the tool: it is 'Not a first look' and references token_wallets as the tool that names holders, implying this tool is used after or in conjunction with it to understand connections. However, it does not explicitly list exclusions or alternatives beyond token_wallets, though the sibling list is extensive. The guidance is sufficient for an agent to route to this tool when relationship analysis is needed.

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