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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantive behavior beyond them: dates are sourced from USDA FSIS charts, oven is fixed at 325F, unstuffed birds only, and — most importantly — a step is judged "past" in the user's local frame, falling back to "past in every US time zone" when no timezone is supplied, with the plan disclosing that in a clock note.

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 first sentence front-loads what the tool does and the second enumerates the output rows, which is good structure. The three timezone-related sentences overlap somewhat and "The plan says so in a clock note" is a slightly padded closing, though no sentence is wholly wasted.

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 7-parameter tool with no output schema, the description does the necessary work by naming what each plan row is and how past/future steps are labeled. It stops short of describing the concrete shape or date/time formatting of the returned plan, which an agent planning a follow-up turn would benefit from.

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?

With 100% schema coverage the baseline is 3, but the description contributes a recommendation the schema does not make ("pass an IANA timezone when you know it") and explains why the timezone matters, namely that time-dependent steps are judged in that local frame. The now_local-vs-timezone precedence it mentions largely restates the schema.

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?

"ThawDay counts back from your dinner hour and names the exact buy, thaw, brine, and roast days" states a precise verb and resource, and enumerating the full set of dated rows (buy, thaw, brine, oven at 325F, sides, rest/carve) makes clear by scope that this is the composite planner rather than the single-value sibling lookups get_roast_time or get_thaw_time.

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?

"Build the dated turkey plan for one dinner" plus "Plans unstuffed birds, 8 to 24 lb" gives a clear scenario and an explicit exclusion (not stuffed, not outside 8-24 lb), which is more than most tools offer. It never names get_roast_time or get_thaw_time as faster alternatives when only one time is needed, so the when-to-use-vs-sibling rule is left implicit.

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