suggest_action_items_from_messages

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

Annotations only declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, but the description goes far beyond: it explicitly states that the tool 'runs in the background', that it returns 'ACKNOWLEDGEMENT ONLY', and that results must be retrieved by polling a listing tool with `status: 'suggested'`. This discloses the asynchronous behavior and the fact that no items are returned directly, which is not inferable from annotations alone.

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?

The description is well-structured with clear sections (USE WHEN, USE INSTEAD, FIRST, EXAMPLE, RETURNS). It front-loads the critical asynchronous behavior and usage context, and every sentence serves a purpose—no filler. The example is concise and the length is appropriate for the tool's complexity.

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?

Given that the tool has a single parameter, no output schema, and a background execution model, the description provides all necessary context: how to trigger, what to expect (acknowledgement only), how to retrieve results (polling with status 'suggested'), and how to obtain the input (from `list_messages`). There is no missing information an agent needs to call this tool correctly.

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?

The schema covers 100% of parameters, with `message_ids` described as 'List of message IDs'. The description adds that message IDs come from `list_messages` (field `results[].id`) and provides an example usage JSON, which goes slightly beyond the schema's basic type info. However, this is mostly supplementary; the schema already documents the parameter adequately, so a baseline 3 is appropriate.

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 clearly states the tool's purpose: 'Queue AI extraction of candidate action items from specific messages.' It specifies the resource ('specific messages'), the action ('extract candidate action items'), and the asynchronous nature ('Runs in the background'). The sibling `suggest_action_items_from_message` (singular) is explicitly contrasted, so an agent can distinguish them immediately.

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 provides explicit usage guidance: 'USE WHEN: Turning a conversation into tasks' and 'USE INSTEAD: 'suggest_action_items_from_message' (singular) for a SINGLE message' and 'create_action_item when you already know the task'. It also instructs to poll `list_my_action_items` or `list_action_items` with status 'suggested' and to get `message_ids` from `list_messages` if needed. This leaves no ambiguity about when to use this tool versus alternatives.

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