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

Annotations already declare readOnly=true and destructive=false, and the description adds valuable runtime behavior: status token variants ('succeeded' in Studio/SeedDance), minimum job duration (≥2 minutes), the exception for TikTok Carousels, and the fact that completed outputs are attached as inline resource links. This is exactly the behavioral context the annotations do not provide.

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 long but every sentence carries decision-relevant information: scope, coverage, statuses, timing, output links, and exceptions. It front-loads the universal purpose and then packs specifics without filler, earning its length.

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 a universal poller that spans many generation tools, the description tells an agent exactly what to poll, which status strings to expect, how long to wait, and which sibling pollers to use instead. The presence of an output schema makes detailed return-type documentation unnecessary, so nothing needed to call it correctly is missing.

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 already describes jobId as accepting jobId or projectId, so coverage is 100%. The description adds value by enumerating which source calls produce jobIds versus projectId (e.g., AI Edit / Character Swap), helping the agent map the correct id form to the originating call. This enrichment justifies above-baseline scoring.

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 opens with a precise verb-object pair ('Poll ANY async VidGuy job by its id') and immediately labels it 'the universal poller.' It enumerates the covered source tools and explicitly names dedicated siblings for exceptions, so an agent can distinguish it from get_video, get_dub_status, and others without opening their schemas.

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?

It states clearly when to use the tool (any async generation) and when not (influencer vault builds / snack packs and dubs have dedicated pollers, named explicitly). It also provides concrete polling cadence guidance (~10s for generations, ~3s for TikTok Carousels) and warns against treating early 'processing' as failure. This is full usage guidance.

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