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

With no annotations, the description carries the full burden; it does disclose the read-only nature and the per-line result taxonomy (ready_new, already_exists, invalid), which is real behavioral value. However it omits what happens past 50 rows, whether failures are partial or all-or-nothing, and whether addresses are checked on-chain or only syntactically.

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?

Four telegraphic sentences, each carrying a distinct fact: the action, the row shape, the return values, and the safety profile. Nothing is padded and the scope constraint is front-loaded.

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?

There is no output schema and no annotations, and the description does explain the three return statuses, which is the right instinct. It is still thin on edge semantics – row-cap overflow, duplicate addresses within a batch, and unsupported chainId values are all unspecified.

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 0%, so the description must compensate. It restates the row shape { address, chainId, nickname? } and adds the non-schema 50-row ceiling, but gives no format semantics for address (hex vs base58) or chainId (numeric string vs chain name), which matters for a validation tool.

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?

'Preview a batch recipient import' names a specific action and resource, and the preview framing implicitly separates it from the mutating propose_recipient_manifest. It stops short of naming a sibling, so an agent must still infer that this does not create anything.

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 word 'Preview' and the 50-row cap imply a pre-flight check before an actual import, but the description never states when to use this instead of propose_recipient_manifest or validate_payout_manifest, nor what to do on failure. Usage is inferable rather than stated.

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