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

Annotations already declare this a read-only, idempotent, non-destructive call, so the safety profile is covered. Beyond that, the description discloses non-obvious behavior: each leg is annualized on its own settlement cycle (1h/4h/8h) and the ranking uses a median over `window` rather than the latest print — exactly the kind of methodological detail that changes how an agent interprets results.

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 the core definition in the first sentence, then the row payload, then the methodology caveat. Three tight sentences with no filler, though the mid-sentence line breaks add visual noise and the closing rationale ('noisy for hourly contracts') is borderline expendable.

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 steps in to describe the row shape (spread in APR points, which venue to long, which to short). For a three-optional-parameter read tool with full schema coverage and clear annotations, this is nearly sufficient; only the sort direction and APR unit convention (percent vs. decimal) are left unstated.

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 all three parameters are already documented, which sets the baseline at 3. The description does add unit and rationale for `window` (median over the last N minutes rather than the noisy latest print), a modest but real value-add beyond the schema; it says nothing about `limit` or `min_venues` that the schema doesn't already cover.

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?

Specific verb+resource framing: coins ranked by funding spread ACROSS exchanges, with the per-row payload (APR point spread, long venue, short venue) spelled out. It distinguishes itself implicitly from single-venue tools like get_funding_rates, but never names the close sibling get_funding_arbitrage, so the boundary is inferred rather than stated.

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 by the methodology (screening coins for cross-venue funding dispersion suitable for carry/arb trades), but there is no explicit when-to-use, when-not-to-use, or pointer to alternatives. With get_funding_arbitrage sitting right next to it in the catalog, the absence of routing guidance is a real gap.

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