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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavior the annotations don't: results are restricted to 'finished meetings', and fields like due date and transcript segment are only present 'when one was resolved' / 'when it can be located', warning the agent about nullable outputs. It omits any mention of pagination despite the cursor/page_size parameters.

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?

Three sentences, front-loaded with the trigger condition before the return shape and filters, with no filler. Slightly more compact would be possible, but each sentence carries distinct information.

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?

An output schema exists, so the description doesn't need to detail return values, yet its brief field list is a helpful preview. For a zero-required, five-parameter list tool it covers triggers, scope, and filters adequately; the remaining gap is pagination/filter-format guidance for the undocumented parameters.

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 only 40% (cursor, status, and meeting_id are undocumented in the schema), so the description must compensate. 'Filter by meeting, status or due date' does map onto three of the five parameters, but it adds no format or value detail (e.g. that status is open/done, that meeting_id is an opaque id) and says nothing about cursor or page_size, leaving a real coverage gap.

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 description gives a specific verb and resource ('Returns action items from the connected user's finished meetings') plus the exact scope, so the agent can tell it apart from siblings like meetnotes_list_recordings, meetnotes_get_transcript, or search without opening a schema. It also enumerates the surface (owner, status, due date, transcript segment) which no sibling tool returns.

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 opening sentence gives explicit trigger phrasing ('Use this when the user asks for action items, tasks, follow-ups, owners, deadlines or pending work'), which maps user intent directly onto the tool. It stops short of naming when NOT to use it or pointing at an alternative such as search/fetch for cross-meeting keyword lookup.

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