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

Annotations already cover idempotency, non-readOnly, non-destructive, and closed-world. The description adds real value beyond them: it discloses that a job consumes one API export allowance, enforces a 30-second duration limit, and returns an exportId — billing/limit context an agent needs before calling.

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?

Five short sentences, each carrying a distinct fact (format, placements, duration limit, allowance/return, idempotency). Front-loaded with the core action; no filler, though the placement sentence is slightly dense.

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 an 8-param mutation tool with an output schema and full annotations, the description covers the essential behaviors (cost, duration precondition, exportId, idempotency retry semantics). The only material gap is the undocumented size/quality parameters.

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 only 25%, so the description must compensate more. It clarifies format (MP4/WebM), the four category placements, variant, and language, but leaves size, quality, projectId, and variantId meaning unexplained. Partial compensation for a low-coverage schema.

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: 'Starts an MP4/WebM export of a saved promo-video variant and language.' It is distinguishable from generate_promo_video and preview_promo_video by the word 'export', though it never explicitly names those siblings or contrasts with them.

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 a hard precondition ('Server duration must be under thirty seconds') and notes the one-allowance cost, but never says when to prefer export over preview_promo_video or when to poll get_promo_video_export for the result. Usage is only implied.

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