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

Annotations only declare readOnlyHint=true, so the description carries most of the behavioral burden and does it well: it discloses the resulting state — source retains its vote at reduced weight, child starts unvoted, both share the same lock end — and it pre-empts the destructive reading of 'split' by asserting no stake leaves the wallet, no NFT is burned, no vote cleared, no fees discarded. That is a genuine reconciliation with readOnlyHint rather than a contradiction. It omits any mention of what the tool actually emits (prepared calldata/transaction) or authority requirements, which is why this is not a 5.

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, front-loaded with the action and its result, followed by a compact negative list of non-effects. The negatives are enumerated efficiently and each carries information (stake, NFT, vote, fees). Slightly dense but nothing is wasted.

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 six-parameter prepare tool with an output schema and only a readOnlyHint annotation, the description supplies the essential missing context: resulting vote state on both tokens, lock-end preservation, and a safety profile. An agent needs no return-value explanation because an output schema exists. Gaps remain around caller authority and the prepared-transaction output, keeping it below 5.

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%, so the schema already documents all six parameters, establishing a baseline of 3. The description adds moderate meaning: 'explicit salt' signals the determinism of the child ID, and 'reduced weight' links amount to the source's post-split voting power. It does not explain the units or constraints of amount beyond the schema, nor clarify the chain_id caveat already present in the schema.

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 a specific verb and resource ('Split a source ve-token') and states the distinguishing mechanism ('explicit salt') plus the deterministic outcome ('return the deterministic child token ID'). An agent can picture exactly what is produced. It stops short of contrasting with the inverse sibling prepare_ve33_merge or with prepare_ve33_reallocation, so sibling differentiation is left implicit.

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 only implied: an agent can infer this is the tool for dividing one ve-lock into two, but there is no explicit 'use when X' clause, no mention of the alternative (merge, increase_stake, reallocation), and no stated prerequisites such as ownership of ve_id. The context needed to choose correctly must be derived from the name and the sibling list.

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