Check 1–12 tasks: status, progress, and the result URL when finished (plus a poster image for videos). Poll every 15–30 seconds while tasks are queued or running.
| Name | Required | Description | Default |
|---|---|---|---|
| task_ids | Yes | 1 to 12 task ids |
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | present only when the call failed | |
| tasks | No | ||
| all_done | Yes | true when no task is queued or running | |
| not_found | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true and a closed-world scope, so safety is covered. The description adds genuinely new context: the polling cadence, the fact that results appear only when finished, and that video tasks carry a poster image. It does not say whether task records expire or how long they remain retrievable, which limits completeness slightly.
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?
Two tightly written sentences: the first covers what is returned, the second covers how to use it. Nothing is redundant and the most important capability is front-loaded.
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 return values need no further explanation, and the description still usefully previews them. Between annotations and schema all the operational essentials are present; only edge cases like id discovery and task expiry are absent.
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% and the single param already documents 'todos' semantics with minItems 1 and maxItems 12. The description's '1–12 tasks' merely restates those bounds and adds no format or id-origin guidance, so the baseline of 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?
States a specific verb and resource ('Check 1–12 tasks') and enumerates what comes back: status, progress, result URL, and a poster image for videos. It implicitly distinguishes itself from list_recent_tasks by taking explicit ids, but never names that sibling, so an agent must infer which one to call.
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 gives explicit operational guidance — 'Poll every 15–30 seconds while tasks are queued or running' — which is exactly the when-to-use information an agent needs. It stops short of exclusions (e.g., 'do not poll finished tasks', 'use list_recent_tasks to discover ids').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
