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

Even though annotations already mark readOnlyHint=true, idempotentHint=true, and openWorldHint=false, the description adds substantial behavioral context: it is always free on the match meter even at zero balance, it consumes one request-unit per address, it requires a minimum of 10 distinct addresses due to aggregate design, and it explains exactly what low vs. high bands mean. This goes well beyond the annotations.

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 front-loaded with the tool's purpose and safety profile ('dry run', 'counts only'), then structured into cost, batch constraints, and band semantics. Every sentence contributes necessary decision-making information, and the prose is dense without being padded.

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?

With no output schema present, the description does the work of explaining what the tool returns: counts in each category and the billing band, plus the low/high band interpretation. It also covers cost, rate-window behavior, minimum/ceiling batch sizes, and where to get per-chain matching rates, so an agent has what it needs to call the tool and interpret the result.

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 schema already documents the address format, minItems, and maxItems at 100% coverage, so the baseline is 3. The description adds meaning beyond the schema by clarifying that the 10-address minimum is about distinct addresses, explaining the per-address request-unit cost, and mentioning the plan's batch ceiling. It slightly falls short of 5 because duplicate-address handling is implied but not fully explicit.

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 names a concrete operation ('dry run over a list of addresses') and the resource (address list estimate) with a specific outcome: counts of indexed, checked-bare, never-seen addresses plus a billing band. It differentiates itself from the resolving sibling by saying 'Counts only, no identities' and 'Use it to decide whether a list is worth resolving,' so an agent can distinguish it without opening schemas.

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 explicitly states when to use the tool: 'Use it to decide whether a list is worth resolving, and which tool to spend on.' It contrasts the low band with a real resolve and the high band with background resolves, and points to the coverage tool and /v1/stats for per-chain rate tables. This gives clear decision context relative to sibling tools.

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