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

The description asserts 'Read-only', but the annotations declare readOnlyHint=false, a direct conflict that an agent will read as possible state mutation. Although the text does disclose the paid side effect (0.01 native USDC per call on Base) and pilot limits, which plausibly explains the false readOnly hint, the two signals contradict each other instead of being reconciled. Flagged as an annotation contradiction.

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?

Five tight sentences, front-loaded with the operation and chain/protocol, followed by semantics, caveats, safety/pricing, and version pin. Every sentence carries information an agent needs (paid call, no USD/profitability claim, tokensOwed caveat). The version string is the only near-optional element, so it falls slightly short of maximally economical.

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 paid, schema-nested read tool with an output schema, the description supplies what structured fields cannot: the cost and pilot limits, the accounting semantics and signed-discrepancy intent, the tokensOwed interpretation caveat, and the explicit absence of valuation/trading/custody claims. Return format need not be explained because an output schema exists.

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 67%, so the baseline is 3. The description adds real meaning by framing the 'reported' object as optional checkpoints for reconciliation and by noting uint128 accounting semantics for the raw amounts, plus the caveat that recorded tokensOwed may include withdrawn principal. However, it says 'one canonical block hash' while the schema parameter is blockNumber (a number whose omission falls back to the provider's safe block), leaving a terminology mismatch rather than clarifying the parameter.

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 names a specific verb and resource (read Base Uniswap V3 NFT and pool state) and scopes it precisely to one canonical block hash, then states the reconciliation job against optional reported raw amounts. It also disambiguates the resource ('not an Aerodrome or V4 position' appears in the schema, and the description pins protocol/chain), so an agent can distinguish it from the unrelated siblings (base_token_allowance, base_token_facts, preview_base_usdc) at a glance.

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 context is implied rather than stated: supplying the optional 'reported' amounts triggers reconciliation, and the block-number parameter is described as a historical pin. There is no explicit when-to-use/when-not statement, no guidance on choosing a block number versus the provider's safe block, and no pointed alternative tool to prefer in other cases. Adjacent siblings are unrelated, so the absence of routing guidance is a modest but real gap.

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