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

No annotations exist, so the description carries the full burden and does well: it discloses that numbers are gross of taker fees, basis moves, and two margin accounts, defines positive_share_7d as a 0-1 share (0.5 = coin flip), and gives the sign convention for mark_gap_bps (positive = entry in your favour). It omits data-source caveats, staleness, and pagination behavior, keeping it short of 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?

Front-loaded with the core purpose, then field definitions, then the alternative and the gross caveat. Dense but each clause carries information; the inline field definitions are slightly verbose but earn their place given there is no output schema.

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 usefully defines the key returned fields (positive_share_7d, current_spread_apr, mark_gap_bps) and the gross caveat, plus a disclaimer. The only meaningful gap is the absence of any parameter documentation for a two-parameter 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 coverage is 0% and neither parameter (limit, min_venues) is mentioned or explained anywhere in the description. An agent cannot tell whether limit caps coins returned or minimum-venue universe size, nor how min_venues filters rows — the description fails to compensate for the schema gap.

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 verb+resource+method: a 'funding carry screener on REALIZED numbers' that picks the venue pair a desk would trade (short richest funding, long cheapest) and reports annualized funding earned over 7 and 30 days. An agent can immediately distinguish it from sibling funding tools like get_funding_rates or get_funding_history.

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?

Explicitly routes the alternative: 'Use get_funding_dispersion for the live spread across all venues,' which implicitly delimits this tool to realized/historical carry. It never states hard exclusions or prerequisites, but the named sibling and the realized-vs-live framing give clear selection context.

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