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

Annotations only declare readOnlyHint=true; the description adds real behavioral detail beyond that: truncation to the token's divisibility so the total is never exceeded (i.e. integer-down rounding, dust left behind), and that the output is a recipients CSV rather than a signed transaction. It does not cover empty-result behavior or size/rate limits on scanning all holders.

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?

Two sentences, both earning their place, with the core mechanism front-loaded and downstream routing last. The inline '(filters: kinds, minAmount, exclude)' list partially duplicates the schema and makes the first sentence dense, which keeps it just below top marks.

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 an 8-parameter, no-output-schema read tool, the description supplies the missing return-value information (recipients CSV) and the numeric guarantee that the sum never exceeds total, plus the handoff targets. What remains unexplained (CSV column layout, empty-holder case) is minor and inferable.

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?

Above the 3 baseline for 75% coverage: the description maps mode to its plain meanings ("equally or pro rata") and names the three filter levers (kinds, minAmount, exclude) in context of filtering holders. It also clarifies the two-resource model implicit in holdersOf vs sendResource by saying holders of one token receive another token.

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?

Specific verb+resource with full mechanism: reads every holder of one resource and splits an amount of another resource among them, equally or pro rata, with truncation. It also names the two downstream consumers, so it is clearly distinguishable from get_resource_holders and the build_*_manifest siblings.

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?

It routes explicitly to build_locker_manifest (operation "airdrop", recommended) or build_bulk_send_manifests as the next step, and the parenthetical 'recommended' expresses a preference. There is no explicit when-not guidance (e.g. for large holder sets or for non-airdrop use cases), so it falls short of the 5 bar.

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