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

Annotations already cover safety (readOnly, idempotent, openWorld=false), so the bar is low, yet the description adds substantial behavioral detail: the trigger day is excluded, all calendar days count including intermediate weekends/holidays, only the last day rolls, holidays use the federal-office observed weekday, and Juneteenth is included. It also discloses explicit non-goals, which prevents misapplication.

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 operation, then progressively hardening constraints and exclusions. Sentences are dense but every one earns its place by disambiguating expected behavior (trigger exclusion, roll-only-last-day, holiday rule). No filler.

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?

An output schema exists so return values need not be explained, and the description fully covers the remaining gaps: scope of the rule, counting mechanics, holiday basis, and explicit non-goals. Nothing an agent needs to invoke this correctly on a legal deadline 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; the description adds value by stating the day range (1–3660), clarifying direction semantics ('after' or 'before'), and noting the absence of a calendar argument entirely — a meaningful constraint not obvious from the schema. It stops short of any additional syntax detail, so not a full 5.

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 precise verb ('count') plus the exact resource and governing rule (Fed. R. Civ. P. 6(a)(1) day-counting), and explicitly contrasts itself with 'Excel WORKDAY' and with business-day-style counting. An agent can distinguish it from count_business_days or add_business_days on the calendar-day-vs-business-day axis without opening the schema.

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 clearly scopes when this applies (Rule 6(a)(1) day periods) and lists explicit exclusions (state holidays, one-off holidays, clerk inaccessibility, Good Friday, Inauguration Day) plus a boundary disclaimer ('does not decide whether a filing is timely'). It never names the sibling alternative count_business_days by name, so routing between the two is left slightly implicit.

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