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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description goes well beyond them: it discloses determinism ('same engine as the app and the Pro Workspace; it never estimates'), the missing-input behavior ('status "missing" and nothing is calculated'), and that output includes the rule/steps and a not-legal-advice notice. What's not covered is other failure modes (invalid dates, >24 periods) or performance.

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?

Dense and front-loaded: the counting rule leads, then edge cases, then scope, then return contents. It is a single long run-on paragraph rather than separated structure, which slightly hurts scanability, but nearly every clause carries information.

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 does the work of describing the return payload (inclusive days, exact and rounded weeks, boundary-dropped flag, next day, steps, legal notice) and covers the key counting edge cases. Minor gaps remain around error handling for malformed dates or exceeding the 24-period cap.

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?

Adds real meaning the schema doesn't: 'both end dates count' clarifies start_date/end_date inclusivity, 'a period that starts the day the previous one ended counts that day once' explains cross-period boundary handling, 'a period held in abeyance counts no weeks' gives semantics for the otherwise undocumented held_in_abeyance flag, and the rounding enum is glossed as rounded down.

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 computation (weeks between dates) with the exact counting convention used by The Comp Desk's CCP/Award calculator, and scopes it explicitly: 'Dates only, no money. New York State only.' That boundary separates it from the many money-producing calculate_* siblings without needing to enumerate 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 clear context for when to reach for this tool (matching how the CCP/Award calculator counts weeks) and exclusions (dates only, no monetary output, NY only). It stops short of naming which sibling to call instead when money or another jurisdiction is involved, so the routing is implied rather than stated.

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