list_recurring_meeting_occurrences

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description still adds real behavioral context: occurrences are synthesized from the recurrence rule except where a real Meeting was materialized, and the result set is unpaged with no offset. It doesn't describe return shape or ordering, but the virtualization caveat is the non-obvious part.

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, then prerequisite, then the filter vocabulary, then the virtualization/pagination caveat. Every line conveys information not present in annotations or schema; nothing is repeated.

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 read-only list tool with no output schema, the description covers prerequisites, filter semantics, virtualization, and pagination behavior. It could go one step further and say what an occurrence object minimally contains (id, start/end, cancelled flag) or how a materialized occurrence is signaled, which matters when chaining to get_meeting or init_recurring_meeting_occurrence.

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 67% and the 'filter' property has no description or enum in the schema, so the description carries the enumeration ('upcoming', 'past', 'cancelled', 'open'), which is essential. It also documents in prose that limit applies only to filter=upcoming and that other filters return the full set, matching the schema's limit description and reinforcing it.

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 ('List virtual occurrences of a recurring meeting') and immediately differentiates the scope from the sibling list tools: this returns occurrences of one series, not meetings or series themselves. An agent can pick this over list_meetings/list_recurring_meetings without opening a 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?

It gives concrete usage context: the OpenProject 17.4+ requirement, the four valid filter values, and the note that this list has no offset/pagination unlike list_meetings/list_recurring_meetings. What's missing is an explicit 'use this when you need future/past occurrences of an existing series' framing and any guidance on when to materialize via init_recurring_meeting_occurrence instead of just listing.

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