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

With no annotations provided, the description carries full burden and handles it thoroughly. It discloses the weekly publication schedule, the 4-hour cache with the 'stale-by-design' caveat, the substring matching semantics of the contract parameter, and exactly what output fields to expect (net positions, % of OI, 4-week net delta). No contradictions with annotations exist.

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?

The description is dense but every clause serves a purpose: what the report is, publication timing, the unfiltered default behavior, the filtered behavior with examples, output components, a trading interpretation heuristic, and caching behavior. There is no fluff, and the structure flows logically from overview to usage to caveats.

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?

For a tool with a single optional parameter and no output schema, the description is unusually complete. It covers default vs. filtered behavior, the fuzzy matching of the parameter, the exact output fields, the data's staleness, and even suggests use cases. There is no meaningful gap that would leave an agent unsure about what this tool does or returns.

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?

The schema provides zero description for the 'contract' parameter, but the description fully compensates: it explains that it's a substring match, gives multiple concrete examples (GOLD, WTI, NATGAS, etc.), specifies the behavior when omitted, and details the output structure for the filtered case. This is exactly the kind of parameter semantics the description should add.

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?

The description clearly identifies the tool as the CFTC Commitments-of-Traders report showing futures positioning by cohort, with specific detail on what is returned both globally and per-contract. It distinguishes itself from the many sibling intel tools by its explicit focus on COT data and cohort breakdowns.

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?

The description explains two clear usage modes: without a filter (top-10 money-manager positions across all contracts) and with a contract filter (5-week history for a specific contract). It also provides interpretive guidance (extreme money-manager longs as exhaustion signal) which implies when an agent would want this data. However, it does not explicitly mention alternatives or when NOT to use this tool, so it falls short of a 5.

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