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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false; the description's "Read-only; does not generate again..." largely restates that safety profile. It does add genuine value by naming the completed return payload (the prepared picker) and by ruling out apply/replace/export side effects, but says nothing about behavior for an unknown or failed job id, nor about polling cadence — the things an agent actually needs for a polling tool.

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 sentences, zero filler, with the positive statement of what is returned front-loaded ahead of the negative scope disambiguation. Every clause earns its place by either describing output or excluding a confusable sibling.

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?

The output schema exists, so the description doesn't owe the agent return-field documentation, and it correctly names the key payload (prepared picker). But with three undocumented parameters at 0% coverage and no guidance on polling vs. one-shot status checks, the definition is thin for a job-status tool with 3 required/optional params.

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% and the description names no parameters at all. projectId and generationJobId are inferable from their names, but replaceVariantId on a declared read-only status call is genuinely puzzling and completely unexplained — an agent has no way to know when to pass it or what it changes about the response.

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: returns status of an existing promo-video preparation job, plus the prepared picker on completion. The closing clause names the four sibling operations it is NOT (generate, apply candidate, replace variant, export), so an agent can separate it from generate_promo_video, apply_promo_video_candidate, clear_promo_video and export_promo_video without opening any schema.

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?

"of an existing ... job" and "when complete" make clear this is a status/poll call on a job id you already hold, and the exclusion list implicitly routes the agent to the mutation siblings. What's missing is explicit sequencing advice — nothing says to call generate_promo_video first, or whether to poll repeatedly until the picker appears.

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