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

Annotations already establish read-only, idempotent, non-destructive semantics, and the description adds substantive behavior: start excluded and destination included, month/year units converting to calendar-day span, the all-weekdays-excluded fallback surfaced in businessDaysRan, and the returned rules/provenance/share link. This is genuine context beyond structured fields, though the exact resolution order for combining years with exclusions is only gestured at.

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 description is dense but front-loaded, leading with the operation before the edge-case rules. A few clauses are jargon-heavy ('become their calendar-day span before matching-day adjustment', the businessDaysRan reference) but each sentence carries operational meaning.

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 11 parameters, exclusion logic, and an output schema already present, the description targets exactly the non-obvious parts: exclusion ordering, the start/destination boundary, and the degenerate all-excluded case. Remaining gaps (per-parameter meaning of region/country, error behavior for missing holiday data) are largely covered by schema descriptions.

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 45% across 11 parameters, so the description must carry weight. It clarifies the unit semantics (nonnegative whole years/months/weeks/days) and the exclusion boundary rule, which the bare schema does not, but it adds nothing about country/region/language/excludeHolidays beyond what schema descriptions already say and does not tie mode to the arithmetic outcome.

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?

The description opens with a specific verb-resource pair ('Add or subtract nonnegative whole years, months, weeks and days'), making the operation unmistakable. It does not explicitly contrast itself with count_days or get_holidays, so an agent must infer the boundary from the sibling names alone.

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?

Usage is only implied: it is for shifting a date by units under specific exclusion rules. There is no explicit 'use this instead of count_days when...' guidance, nor any note about prerequisites such as needing country before excludeHolidays (that appears only in the schema).

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