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

The description discloses destructive side effects beyond the annotations: the default preserve_existing_locks path claims, splits and votes with nothing burned, extended or withdrawn, while compact_max_lock burns every merged source NFT and extends the survivor to four years, and it says so explicitly. This is exactly the mutation-risk detail an agent needs; readOnlyHint=true is consistent because the tool only compiles decodable calls rather than executing them.

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 outcome, then the safety contrast between the two paths, then the workflow prerequisite and handoff instructions. Dense and mostly waste-free, though the 25-target limit and the compact_max_lock semantics are restated in both the description and the schema.

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?

Given an output schema, the description does not need to explain return values, yet it still tells the agent what to do with the result: hand the wallet the survivor, every burned source, the extension, and the decoded calls. It also points to ekubo://docs/ve33-workflow for deeper detail, covering the full prepare-then-execute loop.

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 100%, so the baseline is 3, but the description adds cross-parameter meaning: current_state_id ties to a specific prior get_ve33_allocations read and fails on state drift, salt_nonce exists because splits create deterministic child IDs, and the target count interacts with strategy (one NFT per target under compact_max_lock vs multiple under preserve_existing_locks). Those relationships are not expressible in the flat 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 first sentence names a specific verb (compile) and resource (current allocation → at most 25 target pool-weight shares) delivered as one atomic batch of decodable VeToken steps. It clearly separates this tool from single-action siblings like prepare_ve33_vote, prepare_ve33_merge, or prepare_ve33_split, since it composes them into one batch.

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 states a hard prerequisite (show get_ve33_allocations first, pass its exact state_id, preparation fails if indexed state changed) and explains the two strategy paths with the default called out explicitly. It stops short of naming when to prefer a simpler sibling such as prepare_ve33_vote for a single vote, leaving that inference to the agent.

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