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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered; the description still adds real behavioral context: as_of clipping to prevent look-ahead bias, a 5,000-row page cap, coverage back to 1986, and a free-tier restriction to the last 12 months. It does not explain how to page past the 5,000-row limit or what a truncated result looks like.

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?

Dense and front-loaded: purpose first, then inputs, then return shape, then coverage/limits. Every sentence carries information, though the return-shape sentence is a long run-on list that would read better split.

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 does the work of describing returned columns and trader categories, plus row caps, historical depth and tier gating — enough for correct selection and invocation of a 4-parameter read tool. The remaining gaps (pagination mechanics, date format, unit/currency of values) are minor but real.

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 only 25%, with as_of being the sole documented parameter; the description compensates by explaining market as a named market code with examples and by framing start/end as a date window with end optional. It still never states the expected date string format for start/end (as_of's schema says YYYY-MM-DD, but that is not generalized), which matters since market is also unconstrained free text.

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?

Opens with the question it answers and names the concrete resource: CFTC Commitments of Traders rows broken out by trader category (managed money, producers, swap dealers, leveraged funds, asset managers) with long/short/net. That is specific enough to separate it from get_futures, get_13f and get_bars without opening any 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 clear invocation context ('Give a market ... and a start date; optionally end') with example market values GOLD and CRUDE_OIL, so an agent knows what inputs select this tool. It stops short of explicitly saying when to prefer it over siblings like get_futures or get_13f, and states no exclusions.

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