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

With zero annotations the description carries the full burden and does real work: it discloses that date units are calendar-aware (DST boundary keeps wall-clock time, P1M clamps on Jan 31) while time units are exact elapsed time, and that '-' subtracts. It does not cover error behavior for malformed durations or the return format, which keeps it from a 5.

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?

Three tight sentences, front-loaded with the core action, followed by the two semantic distinctions an agent would otherwise get wrong. Every clause carries information; nothing is padding.

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?

Complete on the dimension that matters most for a 3-param arithmetic tool: how the units interact with timezones. Gaps remain around failure modes (invalid duration strings) and the shape of the returned value, which matters somewhat since there is no output schema.

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, but the description adds genuine interpretive meaning: the Y/M/D vs H/M/S distinction changes how the duration string is applied, and the '-' prefix note reinforces the subtraction syntax. The timezone explanation largely overlaps with the schema's own text, limiting the upside.

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 and resource ('Add an ISO-8601 duration to a timestamp') plus the scoping dimension ('in a timezone'). This is clearly distinct from siblings like convert_timezone and time_between, which either shift zones or compute differences rather than shifting a timestamp by a duration.

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 gives functional context that implies when to use it (shifting a timestamp by a duration, with subtraction via a '-' prefix), and the calendar-vs-time semantics help an agent decide whether this is the right tool. It never explicitly names alternatives or exclusion conditions, so it falls short of a 5.

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