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

Annotations already declare readOnly, idempotent, non-destructive, openWorld behavior, so the safety profile is covered. The description adds genuinely non-derivable context: the per-mint pricing ($0.0015), the $0.01 minimum total, and the crossover point at which batching beats individual snapshots.

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?

Three sentences, front-loaded with what is returned, then cost, then use case — every sentence carries information. Minor redundancy in 'Priced per mint at $0.0015 per mint' costs it a point.

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?

Single required parameter, no output schema, and the description names the return contents (scores, verdicts, ranking) plus pricing and range limits. An agent has enough to call it correctly, though the shape of the comparison output is only named, not characterized.

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% and the schema already explains the plain-address vs chain:address convention. The description only restates the 2-10 range and cross-chain support, adding no syntax or format detail beyond the schema, so the baseline of 3 applies.

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?

States a specific verb (compare/side-by-side ranking), the resource (2-10 tokens on any chain), and the deliverable (watchdog scores, verdicts, ranking) in one request. The phrase 'one request' versus 'one call per token' implicitly distinguishes it from the single-token sibling get_token_snapshot.

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?

Gives concrete usage context: 'Good for screening a watchlist in one call instead of one call per token,' plus a cost-driven rule of thumb (cheaper than separate snapshots at 7+ tokens). No explicit when-not-to-use case, which keeps it just short of a 5.

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