databutler-calendar

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond annotations: data provenance ('from the official lists and statutes'), verification status ('nonOfficial: true' for unverified entries), coverage behavior ('covered:false with the nearest matches'), and detailed return contents for each kind. This is exactly the extra context the dimension rewards.

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 front-loaded with a clear summary sentence, and nearly every clause carries specific information. However, it is a single dense paragraph with long semicolon-separated lists, making it harder to scan than a structured format would be. The length is justified by the tool's complexity, but the lack of visual structure detracts from conciseness.

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 no output schema, the description carries the burden of explaining return contents, and it does so thoroughly for all three kinds (holiday dates and weekdays, tax-year periods with statutes, DST rules with computed dates). Annotations cover safety, and the description adds coverage boundaries, verification flags, defaults, and synonym resolution. Nothing essential for correct invocation appears to be missing.

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 description coverage is 100%, so the baseline is 3, but the description adds rich parameter semantics beyond the schema. It specifies which countries are supported per kind (e.g., kind=holidays supports uk, us, de, fr; kind=tax-year supports nine countries), explains region codes and name resolution (Bavaria resolves to de with region BY), and documents synonym acceptance. This meaningfully enhances how an agent maps values to parameters.

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 opening sentence states a specific verb+resource: looking up public holidays, tax-year dates, and DST switches for one country in 2026–2028. It clearly enumerates the three kinds and their scope, so an agent knows exactly what the tool returns. However, it never mentions the sibling tool next_holiday, so it does not explicitly distinguish itself from that alternative.

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 explains coverage limitations (e.g., 'unknown countries, regions and years answer covered:false with the nearest matches') but gives no guidance on when to use this tool versus alternatives. There is no mention of the sibling next_holiday or any when-to-use/when-not-to-use context. An agent must infer usage from the enumerated kinds alone.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial extra context: the data ends in 2028, a later date returns covered:false with the last covered date, and the data comes from a monthly snapshot of official lists with the source URL. That is exactly the kind of behavioral disclosure annotations cannot carry.

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?

Information-dense and front-loaded — the core purpose and return shape come first, with coverage limits and provenance last. It is a single long, clause-heavy sentence, but nearly every clause carries distinct information, so the length is earned rather than padded.

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 no output schema, the description carries the full burden and does so: it lists the returned fields, the three-following lookahead, the on-date case, the data horizon, and the covered:false failure mode. An agent has everything needed to call it and interpret the result.

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 real meaning beyond the schema: it clarifies that the boundary is strictly exclusive, spells out the per-country region model (UK nations, US federal with OPM observed-date ordering, German Länder, French zones), and notes the region defaults. This goes past restating the schema.

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 ('The next public holiday strictly after a date') and enumerates exactly what is returned (name, date, weekday, days until, the three that follow, any holiday on the date itself). It also differentiates itself from the sibling by deferring region semantics to calendar_facts, so an agent can separate the two without opening either 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?

Gives clear context: default 'today' when no date is supplied, the 'strictly after' semantics, and the supported countries. It points to calendar_facts for the region vocabulary but never states when an agent should prefer calendar_facts over this tool, so it stops short of explicit alternative routing.

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