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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior. The description adds a genuine boundary the annotations cannot express: it compares published aggregates only and does not recommend trades, plus it enumerates returned fields (codes, dates, long/short/net, open interest, ranking, provenance) since no output schema exists.

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-loads the verb, resource, and cardinality in the first sentence, then use cases, then the boundary. Four sentences with no filler; the return-field enumeration is justified because no output schema is provided, though it is the longest and least critical clause.

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?

Covers scope, cardinality, cross-parameter coupling, example intents, return contents, and an advisory boundary. With no output schema, the description takes on the job of describing results and does so; nothing an agent needs to invoke this correctly is missing.

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 the baseline is 3, but the description adds real semantic coupling beyond the schema: all compared markets must share one consistent report family, scope, and trader category, which explains why report_type/category are single scalars applied across the array rather than per-market. It also restates the 2-8 bound as a hard constraint.

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 (compare) and resource (latest reported CFTC COT position) with an explicit cardinality bound (two to eight contract markets). This cleanly separates it from the sibling cftc_cot_latest (single market) and cftc_cot_history (time series) without needing to name them.

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 two concrete triggering scenarios ('compare managed-money positioning in oil, gold, and copper', 'which selected market has the largest commercial net position?'), which tells the agent exactly what class of question this answers. It does not, however, explicitly name alternative tools or state when not to use it (e.g. for a single market, use cftc_cot_latest).

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