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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context in revealing that media URLs are 'signed' (i.e., time-limited), but says nothing about job-state semantics, polling cadence, or behavior when the job has not finished.

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?

A single tight sentence with the action front-loaded and zero filler. Every clause contributes (polling intent, script output, media URL output).

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?

With no output schema, the description must carry return-value semantics, and it does name the two payload classes. However, for a polling tool it omits the critical completeness signal — how to tell a job is finished, and what a pending/failed job returns — leaving a real gap.

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 description coverage is 0% — jobId carries only type/format constraints with no prose. The description indirectly ties jobId to a 'content job', which is a weak but real anchor, and the parameter is largely self-evident given the tool name. No format, sourcing, or error semantics are added.

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 (poll/retrieve) and resource (content job) and names what it returns (scripts plus signed rendered-media URLs). It does not, however, explicitly distinguish itself from the very similar sibling get_clip_job, so an agent must infer the content-vs-clip split.

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?

'Poll a content job' implies the usage pattern (repeatedly call after create_content_job until complete), which is more than nothing. But there is no explicit when-to-use, no mention of the get_clip_job alternative, and no statement of what to do when the job is still pending.

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