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

Beyond readOnlyHint=true, the description adds that the operation uses an exact approval and that 'no existing NFT, vote, fee balance, or ownership is changed' — meaningful scoping context. However, it never states that this *prepares* a transaction rather than executing it, leaving a real tension with the readOnlyHint annotation that the agent must resolve on its own.

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 and kept to two compact clauses with no filler. The second clause is dense — it packs default behavior and a safety guarantee together — but every word carries information.

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 an 8-parameter tool with an output schema and high schema coverage, the description covers purpose, default behavior, and state-safety adequately. The main omission is clarifying whether the call only builds calldata for signing, which matters given the readOnlyHint annotation.

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 88%, so the schema already documents salt, amount, chain_id, and the max_duration/duration_seconds pairing. The description restates the max-duration default and the optionality of a shorter duration, adding only marginal meaning beyond the structured fields.

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 ('Create a new VeToken stake') and adds the distinguishing detail of an 'exact stake-token approval'. The word 'new' implicitly separates it from prepare_ve33_increase_stake/extend/merge, but no sibling is named explicitly, so the differentiation is left for the agent to infer.

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?

Gives a default rule ('Max duration is the safe default for new stakes; an explicit shorter duration is optional'), which is useful parameter guidance. It does not say when to pick this tool over prepare_ve33_increase_stake or prepare_ve33_extend, nor does it mention prerequisites such as sourcing chain_id/ve_token from get_ve33_allocations (that only appears in the schema).

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