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

With readOnlyHint=true already signaling no side effects, the description adds substantial domain context: one transaction per resource per 40 recipients, single signature for create+batch, badge holder gating, only the claimant account can claim, and allowRecover's effect on unclaimed tokens. The notable gap is that it never states the tool returns an unsigned manifest that must then be signed/submitted — the mutation-sounding language ('takes back', 'airdrop') relies on the title to disambiguate.

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?

It is a single dense run-on sentence with heavy nested parentheses and quoted sub-conditions, which is hard to parse for a 14-parameter tool. The opening marketing line ('The right way to airdrop on Radix') costs space without adding selection value, and the per-operation content would read far better as a short list.

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 14-parameter, 5-operation builder with no output schema, the description covers operational semantics well but omits what a caller needs next: what the tool returns, whether the manifest must be signed/previewed with preview_transaction, and the 'Badges are resolved from the account' line is left unexplained. Adequate but with real gaps at the front and back of the workflow.

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 93%, so parameter-level meaning is already documented; the description's value is cross-parameter conditional logic the schema cannot express (recipients also triggers a first batch during create; claim vs lockers alternates; tryDirectSend only matters with recipients). It stops short of explaining the recipients CSV shape or the two-column/defaultResource line format.

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 the concrete resource (AccountLocker manifests) and enumerates the five operations (create, airdrop, recover, recoverAll, claim), so the agent knows exactly what surface the tool covers. It does not explicitly contrast with the closest sibling, build_bulk_send_manifests, leaving the 'airdrop' vs 'plain send' boundary to be inferred from the opening line.

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?

There is rich guidance on which operation applies to which situation (create vs airdrop vs recover vs claim, and tryDirectSend behavior). However, this is operation selection within the tool, not tool selection: nothing says when to use this instead of build_bulk_send_manifests, plan_holder_distribution, or build_manifest_from_template, which is the agent's harder decision.

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