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

Annotations already cover read-only/idempotent safety, but the description adds genuinely non-obvious context: coverage of 139 markets since 2007, the exact back-adjustment relation (adjusted = raw + back_adjustment), and the caveat that the current front month's next roll date is estimated rather than actual. That estimate caveat is the kind of disclosure an agent needs and could not infer from annotations.

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 resource and coverage, then the field list, then the formula, then the invocation instruction. It is a dense paragraph, but every clause carries information an agent would otherwise have to guess; minor cost is the slightly run-on field enumeration.

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 carries the burden of describing the returned record fields and does so in detail, plus the estimation caveat. The remaining gap is the two undocumented date parameters, which leaves the agent guessing about the time-filter contract.

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 only 33% — root is described in-schema and the description reinforces it with examples and the ALL sentinel, which is useful. But start and end are bare strings with no explanation in either place; the description's 'since 2007' hints at a date-range scope without stating format, defaults, or whether they filter by roll date or contract date.

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 (roll calendar for futures markets) and enumerates exactly what each record contains: first/last front-month dates, expiry, next contract, roll date, trading days before expiry, and back-adjustment. This clearly separates it from the sibling get_futures, which returns price data rather than contract-roll metadata.

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 closing instruction 'Give root (ES, CL, GC ...) or ALL' guides invocation but is really parameter usage, not when-to-use guidance. Nothing tells the agent when to prefer this over get_futures, or whether it should be used alongside a bars request to build a continuous series.

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