utilpeek: build an .ics calendar file from 1-50 events given as JSON

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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive), while the description adds substantial behavior: no network access and nothing persisted, deterministic derived uids, exact timezone serialization rules, all-day inclusive-end handling, and a 422-with-event-name error contract that is explicitly not charged. This is far beyond what the annotations convey (the openWorldHint=true annotation is arguably imprecise against 'pure computation', but it does not contradict the safety hints).

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?

Front-loaded with purpose and the sibling alternative, then output shape, then edge-case serialization rules, with pricing/limits/docs trailing. Dense and mostly waste-free, though '1-50 events' is repeated three times (title, description, schema) and the billing snippet sits mid-paragraph.

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 multi-field, nested-input generator, the description covers what the agent must know before invoking: input shape, defaults, serialization semantics, failure mode, cost, and a docs link. An output schema exists, yet the description still usefully names the return artifacts (VCALENDAR text, base64, data: URI, uids), leaving nothing critical unstated.

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 would be 3, but the description adds genuine semantics the schema omits: how a zoned start becomes TZID=<IANA name> with no VTIMEZONE block, how an offset becomes UTC, how a plain local time stays floating, and that all-day `end` is inclusive. These interpretation rules are the main thing an agent could get wrong.

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 ('Build an iCalendar file from JSON events') and immediately names the sibling it is not ('To read an .ics file use parse_ics'), so the agent can distinguish it from parse_ics without opening either schema. Scope (1-50 events) and output format (RFC 5545 VCALENDAR text) are also pinned down.

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 routes the agent explicitly: build here, read with parse_ics. It supplies context an agent needs before calling (pure computation, no network, nothing stored, cost and free-tier limits, typical latency) but never states a positive when-to-use condition for this tool beyond the implied 'you have JSON events and need an .ics'.

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