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

With no annotations, the description carries the full burden and does disclose real behavioral constraints: a 50-line cap, an allowlist requirement, a same-chain requirement relative to fromWalletId, and a cooldown gate. 'Preview' also signals non-mutation. What is missing is what the preview actually returns (per-line errors vs. a summary), whether a failed validation raises or reports, and any auth or quota context.

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 tight sentences: purpose and limit first, then the line shape, then the eligibility constraints. No filler, and the most decision-relevant facts are 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?

For a two-parameter tool with a nested line array, no output schema, and no annotations, the description covers invocation prerequisites well but leaves the return contract and the source of recipient/amount data undefined. An agent knows how to call it but not exactly what to expect back or how to recover from a validation failure.

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?

With only 50% schema coverage, the description compensates reasonably: it restates the line object shape including that memo is optional, clarifies that fromWalletId drives the chain constraint, and explains that recipientId must be allowlisted. It does not say where recipientId values come from (e.g., list_recipients), which leaves one gap.

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 ('Preview') and resource ('batch payroll/payout'), making clear this is a non-committal validation step rather than an execution. It does not explicitly name the sibling it precedes (propose_payout_manifest), so the differentiation is inferred from the word 'Preview' rather than declared.

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?

Usage is implied: an agent can infer this is the dry-run step before proposing a payout batch, and the preconditions (allowlist, same chain, cooldown) hint at when a call will fail. However, there is no explicit 'use this before X' or 'do not use this to execute' statement, and the closely related siblings propose_payout_manifest and validate_recipient_manifest are never mentioned.

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