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

Annotations already cover readOnly/idempotent/non-destructive, and the description still adds genuinely new operational context: a required Authorization: Bearer arb_… Pro token and the fact that the anonymous tier has no access. It also discloses the analytical scope (including rate-sensitivity and capacity), so cost and auth expectations are set before the call.

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 what gets computed, then the key's origin, then the auth gate — no filler. The first sentence is a dense comma-list of outputs, which is information-rich but slightly hard to scan; bullets or grouping would improve it marginally.

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 no output schema, the description carries the return-value burden and does so by enumerating every computed figure, plus prerequisites and auth. Remaining gaps are minor: units/shape of the response, latency or rate limits, and what "settled 7/30-day replay" concretely returns are left implicit.

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 100%, so the schema already documents notional, pair_key and holding_hours, establishing a baseline of 3. The description adds provenance beyond the schema's vague "pair_key from another tool" by naming the two tools that produce a valid key, which is the parameter detail most likely to cause a failed call.

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 opens with a specific verb+resource ("Full calculation of one pair") and then enumerates the exact outputs — funding per leg, settlement count, taker fees, VWAP/slippage, carry, net, halved-rate net, breakeven, capacity, 7/30-day replay. That enumeration is far more specific than any sibling (pair_history, execution_cost, holding_scenarios) and lets an agent tell them apart without opening the 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 real workflow prerequisite: pair_key must come from best_opportunities or coin_overview, which routes the agent to the correct upstream tool. It also states an eligibility gate (Pro API token required, unavailable on anonymous tier). It stops short of naming an alternative for simpler cost questions (execution_cost, manual_calculator), so not a full when/when-not.

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