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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses real behavioral facts: the clip URL is deleted by Higgsfield after 7 days, a failed or flagged request terminates the job with billing only for work completed, the call itself is free, and the response carries charge amount plus TikTok/Instagram bio links. That is exactly the context annotations cannot convey.

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?

All the content is useful, but it is delivered as one long run-on sentence laced with parentheticals ('(then ugc_start with frames ok or stop)', '(download it now: ...)', '(utm tags for a site, ...)'), which makes it hard to scan. A state-by-state list would front-load the polling loop far better.

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 single-parameter status poll with no output schema, the description covers the full state machine, terminal/failure behavior, billing, retention, and the payload fields. The only gap is operational guidance on how often to poll, which would make it fully self-sufficient.

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 'job' parameter is already documented as 'The job from ugc_start'. The description only reinforces the provenance of that ID ('from ugc_start') without adding format or validation detail, so the schema does the heavy lifting and 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?

The description opens with a specific verb and resource: 'Poll an AI presenter video from ugc_start', then enumerates the exact lifecycle states the poll can return (images being made, images ready, clip being made, done). This clearly separates it from the sibling ugc_start, which initiates rather than observes the job.

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 gives explicit routing: after the two images are ready, go back to ugc_start 'with frames ok or stop', and on completion 'download it now' before the 7-day deletion. What's missing is any guidance on polling cadence or how many times to call it, which an agent doing repeated polling would want.

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