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

The description explicitly says it is 'Destructive to the sources' and that 'the source NFT is burned', while annotations declare readOnlyHint=true. Regardless of the rich behavioral detail about fee claiming, vote clearing, and destination lock end, this is a direct contradiction of the structured safety signal and would badly mislead an agent's risk assessment.

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?

Front-loaded with the action, then consequences, then the key eligibility constraint. Three dense sentences with no filler, though the last sentence is slightly convoluted ('which is why no source may end later than it').

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?

A complex, multi-step, nested-object tool with an output schema, so return values need not be described; the description does cover atomicity, fee claiming, vote clearing, and the lock-end rule. But the destructive-vs-readOnly conflict is an incompleteness that no amount of behavioral prose compensates for until the annotations are reconciled.

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?

Adds real meaning beyond the 71%-covered schema: it explains that sources require pre-claims, that the source IDs are reported in the plan, that the destination retains its own lock end (constraining valid source sets), and that the resulting vote is selected in the same batch. It does not clarify chain_id/ve_token provenance, but the schema already does.

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 ('Prepare fee-safe merging of one or more source NFTs into a destination') and scopes the result as an atomic batch of decodable steps. This is readily distinguishable from siblings like prepare_ve33_split, prepare_ve33_reallocation, and prepare_ve33_increase_stake.

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 the merge framing and one eligibility constraint is given ('no source may end later than it'), which helps an agent decide feasibility. However, it never names alternative tools or states when not to use this one (e.g. single-source top-ups should use increase_stake).

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