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

Beyond the annotations (which only say non-readonly, open-world, non-destructive), the description discloses that nothing is signed server-side, that signing order is wallet-then-mint, that the signUrl path returns a preview-only tx, and that constraints like the 1232-byte limit, fresh blockhash, and full simulation apply. It even enumerates response artifacts (HMAC permit, summary, signUrl) despite there being no output schema.

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?

The strongest constraint and the preferred path are front-loaded, and almost every clause carries new information. The telegraphic fragments ('HMAC permit, summary, signUrl.') and stacked clauses make it dense to parse, slightly reducing readability without wasting much space.

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 11-parameter, non-idempotent preparation tool with no output schema, the description covers the signing model, the two workflow branches, size/simulation guarantees, and the shape of the response. What is missing is semantics for the pricing and preset parameters, which an agent must guess from names and defaults alone.

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?

With only 45% schema description coverage across 11 parameters, the description compensates strongly for the pivotal one — nftMint — explaining why to supply it and when to omit it. However, it says nothing about minPrice/maxPrice, rangePreset, resaleFloorBps, slippageToleranceBps, or inputKind, which remain bare names with defaults. That is adequate where the schema carries the load but leaves real gaps given the low coverage.

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 opening sentence names a specific verb and artifact — 'Prepare an unsigned, fully-simulated transaction that opens a new CLMM position' — which is unmistakable against siblings like submit_open_position and submit_signed_transaction. It also explicitly rules out submit_signed_transaction with a reason (two required signers), so an agent can distinguish intent 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 preferred path ('Prefer passing nftMint ... so the server never signs') with the rationale, an explicit fallback condition ('Without nftMint, open signUrl'), and an explicit non-use case ('Not submit_signed_transaction'). The two-branch workflow, including the ordering of wallet vs mint signatures, leaves little to inference.

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