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

With no annotations, the description carries the full burden and does disclose key operating traits: cost of €0.0005 per call, the required 'Authorization: Bearer' credential, and the substantive behavior that add_business_days skips weekends and public holidays. It does not say what happens on invalid tz names, missing required per-op params, or whether errors are billed, leaving a meaningful gap for a mutating-cost, multi-op tool.

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 definition is front-loaded with the three ops and their distinct behaviors, then a compact parameter glossary — dense but efficiently structured with no filler. The parameter list runs as one semicolon-chained block, which is readable but slightly harder to scan than a per-op grouping.

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 ten-parameter, three-operation tool with no annotations, the description supplies op semantics, per-op param mapping, cost and auth — and an output schema exists so return values need not be described. The remaining gap is operational failure modes and per-op required-parameter rules, which matter given all params are optional at the schema level.

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 0% (all ten params are untyped nullables with bare titles), so the description must compensate, and it does: every parameter is mapped to its operation, 'days: integer, can be negative' explains semantics, 'country: ISO country code for holidays' and 'subdiv: state/region code' add format and meaning. Gaps remain: 'days' is described as an integer while the schema types it as a string, and there is no stated default timezone for 'time'/'start' when 'source' is omitted.

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 names three specific operations with verbs and resources — 'convert moves an ISO time between IANA timezones', 'diff returns the span between two ISO times', 'add_business_days steps N working days' — so an agent knows exactly what the tool does and can distinguish it from siblings like unit_convert or holidays without opening the schema.

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?

Each op is paired with the parameters it consumes and the result it produces, plus an explicit default ('op: convert (default)') and the note that business days are only added 'if country is given'. It lacks explicit when-not guidance or a pointer to the nearest alternative (e.g. holidays or unit_convert), which keeps it 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.