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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine context the annotations don't: publication cadence (weekly), the two upstream data sources, and the explicit caveat that output is raw data rather than a trading signal. It says nothing about update lag, coverage gaps, or response size with weeks>0.

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 sources, then returned fields, then the zero-arg behavior — a sensible order with no filler. The asset-class enumeration is the only slightly padded stretch, though it does help an agent judge applicability.

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 compensates by enumerating the returned metrics (net position, % OI, week change, 52/156-week COT index, crowding, other trader groups). Remaining gaps are modest: no note on data freshness or volume when requesting up to 520 weeks of history.

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% and all three parameters are documented with examples and bounds, so the schema carries the load. The description adds marginal meaning by mapping "optional weekly history" to weeks and clarifying that the zero-argument case returns every market's latest reading, but it doesn't explain how terms matching interacts with markets.

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?

Names a specific verb+resource (weekly speculative positioning in futures) and pins down the exact sources: CFTC Commitments of Traders for US-listed futures and ESMA MiFID II reports for Dutch TTF gas. The asset-class enumeration and the field list (net position, % of open interest, COT index, crowding) make it unmistakable against siblings like get_yield_curves or get_policy_rates.

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?

"No arguments lists every market's latest reading" gives one concrete invocation pattern, and "Plain data, not a signal" frames the intended use. But there is no explicit when-to-use/when-not versus alternatives, and no guidance on choosing between filtering by 'terms' (group/name) and 'markets' (keys) in a real workflow.

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