update_meeting_agenda_item

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

With destructiveHint=true and idempotentHint=false already declared, the description adds real behavioral facts the annotations cannot: a version gate, rejection on closed meetings, and the side effect that each confirmed update touches the meeting's own timestamp. It stops short of saying what permissions are needed or what the response contains, but the meaningful surprises are disclosed.

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?

Four short sentences, front-loaded with the operation and its partial-update rule, then constraints, then the sibling pointer. Nothing is repeated from the schema and no sentence is filler.

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 an 8-parameter destructive mutation with no output schema, the definition covers versioning, closed-meeting rejection, partial-update semantics, and a side effect, with preview/confirm behavior carried by the confirm parameter. Only permission requirements and what a successful call returns are left unmentioned, which is a minor residual gap.

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 per-field rules (50k Markdown limit, "" clears notes, work_package_id display-id format, section moves within a series) already live in the schema. The description still earns above baseline by stating the null/omitted convention up front, which is the one cross-parameter semantic an agent could misread as "clear this field".

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 ("Update one agenda item of a meeting") and immediately scopes it with "omitted fields stay unchanged", which is a partial-update semantic an agent must know. It also names the sibling tool that handles a nearby but different concern (update_meeting_outcome), so it is distinguishable from the other meeting_* mutators 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?

Gives a hard precondition ("Requires OpenProject 17.6+"), an exclusion ("Rejected while the meeting is closed"), and routes outcome edits to update_meeting_outcome. It does not say when to create a new item versus update an existing one, but the use/avoid signals present are concrete and actionable.

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