List Unprocessed Messages

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

readOnlyHint=true already tells the agent this is a safe read, and the description adds real domain context beyond that: messages are retained rather than dropped, the originating flow keeps running, and this is the default error-handling destination. It does not mention ordering or whether results are paginated across the full backlog, which limits it to a 4.

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 short sentences with the core definition first, the operational context second, and the workflow next-step last. Every sentence contributes distinct information; there is no restatement of the title or 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?

Adequate for a read-only listing tool with no output schema: the agent knows what population is returned and what to do next. The remaining gap is the shape of a listed message (which fields identify a failure) and default ordering, though get_unprocessed_message plausibly covers detail retrieval.

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 description never mentions filtering by flow, execution, or result window, so it adds no meaning beyond the schema. Coverage is 50%, but the two undocumented parameters (limit/offset) are self-describing pagination fields with defaults and bounds, leaving the documented filter fields to carry the semantics. Baseline 3 applies.

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?

Uses a specific verb and resource ('List messages that failed processing') and immediately disambiguates the concept by contrasting it with dropping ('parked instead of being dropped'). It also explains the mechanism that populates this list ('Stop execution' / onError: storeUnprocessed), making it clearly distinct from list_flows and get_unprocessed_message.

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 clear when-to-use ('find out what broke') and routes the agent forward to retry_unprocessed_message after remediation, which is an explicit alternative path. It stops short of stating when not to use this over get_unprocessed_message for inspecting a single item, so it is strong but not exhaustive.

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