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

readOnlyHint=true is consistent with a transaction-preparation tool, and the description reinforces that with 'No NFT is burned and no stake leaves the wallet.' Beyond the annotations it discloses real behavioral traits: extension clears the existing vote, fees are claimed atomically before extension to preserve pending voter fees, and the end time can only move later. That is substantially more than the readOnlyHint tells an agent.

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?

Information is front-loaded: mode selection comes first, then the effect of extending, then the safety reassurances and follow-up. Every sentence carries distinct information, though the first sentence is heavily compound and takes a second read to parse.

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 7-parameter prepare tool with a nested PoolKey object, an output schema, and annotations already covering the safety profile, the description covers the remaining agent-relevant unknowns: conditional parameters, the side effect on the vote, and the next step. Nothing needed to call it correctly appears to be missing.

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 71% and the description closes the important gaps: it explains when current_pool_key is required versus omitted, and that max_duration=true must be a deliberate user decision rather than a default. The chain_id/ve_token pairing and duration_seconds semantics are left to the schema, which already documents the former adequately.

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 opens with a specific verb and resource ('Prepare a direct extension for an unvoted VeToken'), then names the two distinct operating modes (plain extension vs. atomic claim-and-extend) and the parameter that selects between them (current_pool_key). It also names the follow-up sibling prepare_ve33_vote, so an agent can place this tool relative to others in the ve33 family without opening a schema.

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 gives a clear conditional rule for current_pool_key ('Omit only for an unvoted VeToken'), an explicit constraint on max_duration ('must be the user's explicit choice'), and a post-call instruction to re-vote with prepare_ve33_vote. What is missing is a comparison against the adjacent alternatives an agent would weigh here — prepare_ve33_increase_stake and prepare_ve33_stake — so the extend-vs-increase decision is left to inference.

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