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

Annotations only supply readOnlyHint=true, so the description's additions matter: 'zero liquidity decrease' and 'Principal remains invested' clarify that the position is not modified, and 'to the sender' clarifies the recipient. The gap is that it does not reconcile the fund-moving language ('take both currencies') with the read-only annotation by stating that it returns an unsigned transaction for signing, nor does it mention approval requirements or deadline handling.

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?

Two tightly packed sentences with no filler; the effect ('principal remains invested') is front-loaded ahead of the prerequisite. The density borders on cryptic ('poke'), but nothing is redundant.

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?

An output schema exists, so return values need not be explained, and the key preconditions are stated. Still, for an 11-parameter transaction-preparation tool it omits whether an approval or prior position lookup is required and does not clarify that the output is a signable transaction rather than an executed collection.

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 73% with nine required params, so the structured schema already documents most fields. The description adds useful linkage — 'pool key' maps to pool_id/token0/token1/fee/tick_spacing and 'hook behavior' points at hooks/hook_data — but it adds no guidance on the deadline value, chain_id selection, or why tick_spacing must match the pool.

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 uses a concrete verb chain ('poke a V4 position with zero liquidity decrease then take both currencies to the sender') that pins down both the mechanism and the effect, and the phrase 'Principal remains invested' cleanly separates it from prepare_uniswap_v4_remove_liquidity. It loses a point because it never states that the tool only *prepares* an unsigned transaction (the behavior implied by the 'prepare_' name), and 'poke' is protocol jargon an agent may not resolve.

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?

'Verify ownership, pool key and hook behavior first' gives real preconditions for calling it. However, it names no alternatives (e.g. prepare_uniswap_v3_collect_fees, prepare_uniswap_v4_remove_liquidity) and gives no explicit when-not condition, leaving the choice between fee collection and liquidity removal to inference from the purpose sentence.

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