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

Annotations only supply readOnlyHint=true; the description adds substantial context beyond that: APR is an annualized snapshot rather than guaranteed yield, its components/denominator/freshness/range must be surfaced, impermanent-loss risk matters, and a partial ranking is signalled by ranking_complete=false requiring a follow-up call. The two-pass protocol with local decoding is behavior an agent could not infer from the schema or annotations.

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?

Three sentences, front-loaded with the return contract before the cautionary yield guidance and the retry protocol. Dense jargon ('boosted-fee', 've(3,3)') is unavoidable domain vocabulary, and every sentence carries a distinct instruction; slight compression could still improve 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?

With an output schema present, annotations covering safety, and 83% schema coverage, the description fills the remaining gaps: precedence in the conversation flow, yield-caveat handling, and the partially-ranked retry path. What it leaves implicit is how chain/token/type filters interact with ranking or what a 'pool-discovery handoff' looks like, but that is modest given an output schema.

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 83% and the ve33_emission_state parameter is already fully documented in the schema, so the description adds little parameter-level meaning. It never explains how token, chain_id, types, min_apr or limit shape the ranking beyond the obvious. Baseline 3 is appropriate when the schema carries the semantics.

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 concrete verb and resource ('Return ... boosted-fee, incentive and projected ve(3,3)-emission opportunities ranked by APR') and enumerates the payload (actionable pools or pool-discovery handoffs, freshness, risk context). That is specific enough to separate it from lookup siblings like get_pool_liquidity or get_ve33_allocations, which return single-pool or allocation data rather than a ranked opportunity list.

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 an explicit sequencing rule ('Call this before asking the user to choose a pair') and a concrete conditional loop: if ranking_complete=false, run local_read_requirement through the wallet, decode locally, and re-call with ve33_emission_state. It does not name competing siblings it should be preferred over, so it stops short of full when/when-not coverage.

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