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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description still adds real context: network matching is by chain and contract and never by ticker, and results carry status plus reasons. It does not disclose pagination/limit behavior or the free-tier constraint (that appears only in the schema), which keeps it from a 5.

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?

One dense sentence plus one supporting sentence, front-loaded with the core trade mechanic and followed by the outputs and the traps view. It is information-dense with essentially no filler, though the comma-laden output enumeration reads as a feature dump rather than a prioritized list.

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?

There is no output schema, so the description carries the return-value burden and does so by enumerating net-after-fees, pre-funded net, capacity thresholds, arrival estimate, hedge cost, status and reasons. What it omits is modest: default behavior (status defaults to executable, limit 10) and what a 'trap' record contains.

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 33% schema description coverage, the description does substantial compensating work: it defines view=traps, ties 'at your size' to notional, implies include_hedge via 'hedge cost on a perp', and explains that status values carry reasons. Only limit and the precise status enum semantics (executable/near/closed/unverified) remain unaddressed by either source.

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 resource and mechanism: buy on one exchange, withdraw on a shared network, sell on another, with net economics after fees, slippage and withdrawal cost. That is far more than a restatement of the name and lets an agent distinguish it from basis or funding tools. It never explicitly names a sibling (e.g. transfer_calculator or basis_trades) to complete the differentiation, so it stops short of a 5.

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 is implied through the mechanics and there is one genuine routing hint: 'view=traps lists spreads that exist only because deposits or withdrawals are closed.' However, there is no explicit when-to-use-this-vs-alternatives guidance against the large sibling set (transfer_calculator, execution_cost, basis_trades), and no statement of prerequisites such as Pro tier for custom notional.

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