compare_tokens

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context: it weighs roles rather than counts, and it discloses that mints outside the index are returned as 'not_covered'. It also mentions a cost ($0.025), which is useful. This goes beyond the annotations by explaining the analytical approach and the coverage limitation.

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 compact and information-dense. It front-loads the purpose with a direct question, then explains the output and the weighting logic, and ends with the coverage caveat. No fluff; every sentence earns its place. Slightly long but efficient.

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 a single parameter fully described by the schema, an output schema exists (verified by context signals), and annotations cover safety, the description provides the missing analytical context: what the output means (roles, weighting) and edge cases (not_covered). It doesn't specify the exact output format, but the output schema likely covers that. Overall, complete for correct invocation.

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% — the 'mints' parameter is described as 'Solana token mint, base58.' The description reinforces that 2-4 mints are required and explains the purpose, but doesn't add much semantic detail beyond the schema. The example in the schema already shows the format. Baseline 3 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 task — compare tokens for shared wallets — and frames it as a question ('Were these tokens run by the same people?'). It explains the output (wallets appearing in more than one mint, with roles). However, it doesn't explicitly distinguish itself from sibling tools like find_serial_insiders or wallet_network, though the focus on cross-token comparison is implicit.

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 gives clear input range (2-4 mints) and hints at when to use it: when investigating whether tokens share operators. It notes that shared holders are common and provides weighting guidance (roles over count), which helps an agent decide if the result is meaningful. It does not explicitly name alternatives or conditions when not to use this tool, but the guidance is reasonably clear.

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