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

Annotations only declare readOnlyHint=true; the description adds real substance beyond that: the output is a diff-based transaction built from current ledger state, the account itself signs, and refused deposits are held in a locker until claimed. It never explicitly says the result is an unsigned manifest returned to the caller rather than submitted, which is a meaningful gap for a build_* tool.

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 sentences, front-loaded with the core action and the diff-from-current-state property, with no filler. The airdrop/locker sentence is a useful caveat but is slightly tangential to invoking the tool.

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 9-parameter build tool with no output schema, the description leaves the agent unclear on what is returned (manifest text? signable payload?) and what the next step is (validate_transaction_manifest, preview_transaction, wallet signing). The conflict/precedence between defaultRule and allow/refuse is also left implicit.

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 description coverage is 100% and the schema already documents each field, including the deposit-badge string format and the 'follow the default rule again' semantics of removeExceptions. The description restates these concepts at a higher level (default rule, always-allowed/always-refused resources, added/removed badges) without adding syntax or precedence rules, so baseline 3 applies.

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 and resource: builds a single transaction that changes who may deposit into an account, and enumerates the kinds of changes it expresses. It does not name the distinguishing sibling (get_deposit_rules, build_manifest_from_template), so the boundary is inferred rather than stated.

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 by 'changes who may deposit into an account' plus the note that deposits can be refused without losing airdrops, which hints at when refusal is appropriate. There is no explicit when-to-use / when-not-to-use guidance, no mention of reading current rules first via get_deposit_rules, and no pointer to alternatives.

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