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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully confirms this is a deterministic computation layered on an existing primitive and enumerates the computed outputs, though it says nothing about edge cases (e.g., zero/negative spread 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?

Front-loaded with purpose and trigger, but the 'compared with primitive.funding_arb' clause restates the first sentence, the math-primitive reference is an awkward sentence fragment, and the Returns list partly duplicates what the schema/verdict already implies.

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 correctly fills the gap by naming the returned fields (netYieldPct, grossProfit, netProfit, breakevenDays, verdict). It omits any note on expected input units beyond the schema or on what drives a 'marginal' classification, but is otherwise sufficient to call the tool.

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 100%, so all six parameters (including the interval_hours enum and fee defaults) are already documented in the schema. The description only gestures at the funding-rate spread concept and adds no syntax or format detail beyond the schema.

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?

States a specific analysis (delta-neutral carry trade / funding arbitrage) plus its distinguishing output (profitable/marginal/loss verdict), and explicitly names the sibling whose math it reuses. An agent can tell it apart from primitive.funding_arb and from workflow.run_funding_arbitrage 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?

Gives a concrete trigger ('use when user asks "is this carry trade worth it?"') and a discriminator against primitive.funding_arb (plain-English verdict vs raw numbers). The named alternative, however, is not in the sibling list shown, so the routing hint is slightly off-target and there is no explicit when-not guidance.

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