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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the description rightly spends its words on non-obvious behavior instead: calendar-first application order and the month-end clamping rule ('Jan 31 plus one month is the last day of February'), plus the supported year range 2000-2100. The clamping rule is exactly the kind of edge case that silently changes results.

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?

Four sentences, front-loaded with purpose, then edge-case rule, then sibling routing, then validity bound. No sentence is filler and nothing important is buried.

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?

Output schema exists, so the description need not enumerate return fields; it nonetheless names them in passing. Between the use cases, arithmetic ordering rule, sibling alternatives and validity range, an agent has everything needed to call this correctly.

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 meaning by framing all four magnitude parameters as operating under a single add/subtract polarity, which explains why direction exists alongside non-negative amounts. It does not restate per-parameter ranges or the YYYY-MM-DD format, but the schema already covers those fully.

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 ('add or subtract years, months, weeks and days to or from a calendar date') with the exact output ('resulting date with its weekday, ISO week and day of the year'). It is unmistakable against siblings like add_time_to_datetime and days_between_dates.

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 concrete use cases ('90 days from today', contract end dates, probation periods, anniversaries) and explicitly routes elsewhere: add_business_days for skipping weekends/holidays, days_between_dates for measuring a gap. When-to-use and when-not-to-use are both present.

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