list_work_package_meeting_agenda_items

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds non-obvious behavior on top: the list is unpaginated server-side with offset/limit applied client-side by the MCP, and text is truncated by default at the server's OPENPROJECT_TEXT_LIMIT with notes_truncated/notes_length signaling real length. These are exactly the traits an agent could otherwise misread from the schema's 'page number' wording.

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 scope and version requirement, then constraints, then the truncation caveat — good ordering with little waste. Slight deduction for awkward mid-sentence line breaks that split clauses ('offset/limit are applied / client-side') and a trailing blank line that add noise without content.

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 must carry the return-value burden, and it does: truncation flags, the text_limit default, and the fact that paging is client-side are all disclosed, while the select enum enumerates available fields. Version and permission gating round out what an agent needs to call it correctly and interpret empty results.

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?

At 80% schema coverage the baseline is 3, and the description earns more by fully explaining text_limit, the one parameter the schema leaves undocumented, including its non-obvious default (server-configured limit, NOT unlimited) and the truncation signaling fields. It also clarifies that offset/limit are client-side, which reinterprets the schema's 'Page size' and '1-based page number' language.

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 (List) and resource (agenda items) with an explicit scope qualifier: 'across all meetings, that link a work package.' That scope phrase is exactly what separates it from the sibling list_meeting_agenda_items, which is meeting-scoped, so an agent can pick the right one 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 useful preconditions ('Requires OpenProject 17.7+') and a visibility exclusion (items in projects outside OPENPROJECT_READ_PROJECTS are omitted), which help an agent decide whether results are trustworthy. However, it never names an alternative (e.g. list_meeting_agenda_items for a single meeting) or states when-not-to-use, so routing is inferred rather than instructed.

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