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

With no annotations present, the description carries the full disclosure burden, and it delivers: signed distances, negative counts when end precedes start, the clamp policy, refusal when only one time parameter is supplied, a note that 0 can be passed intentionally, and a guarantee of exact integer arithmetic. Said behavior goes well beyond basic tool documentation and prevents common misinferences.

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 appropriately so, since there is no output schema and no annotations to lean on. It is front-loaded with the core definition and then systematically adds edge cases, return-field semantics, and the exactness guarantee. The middle long sentence bundling 'ticks', 'time', and the pair rule is somewhat harder to parse, so it loses one point for structure.

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 tool with five parameters, zero schema coverage, and no output schema, the description covers the essential operational surface: input semantics, time-pair constraints, output fields, edge-case behavior, and the relationship to add_to_date. Its main remaining weakness is that the concrete structure of the 'calendar', 'start', and 'end' objects is not spelled out, leaving some ambiguity for an agent constructing arguments from scratch.

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?

The schema provides no textual documentation for the parameters—only empty objects and null defaults—so the description must compensate. It supplies meaning for start and end as dates, explains start_time and end_time semantics including the 'pass 0' rule, and connects the calendar parameter to the breakdown policy and clamp behavior. It does not fully specify the internal shape of the calendar or date objects, which is a gap, but the semantic guidance is strong.

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 precise definition—the distance between two dates—and then explicitly separates the two meanings: exact signed 'days' versus a 'calendar' breakdown of years, months, and days. This level of specificity, plus naming add_to_date as the inverse operation, makes the tool's role unmistakable among many calendar sibling tools.

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 sets clear context: use this tool when you need the exact distance between two dates, with integer arithmetic and a calendar-aware breakdown. It also gives operational rules such as 'Give both or neither: one alone is refused' and points to add_to_date for the inverse direction. It does not, however, enumerate explicit exclusion scenarios versus each alternative sibling, so it stops short of a perfect routing guide.

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