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

Annotations already cover readOnlyHint/idempotentHint, so the redundant 'Read-only' adds nothing, but the description contributes real behavioral context: the download URL is short-lived and failed exports are refunded. Those are consequences an agent cannot get from the schema. It omits whether progress is a percentage or stage label.

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?

Four short sentences, front-loaded with the outcome and the wait behavior, and every clause carries information except the trailing 'Read-only' which duplicates the annotations.

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?

An output schema exists, so return-value explanation is unnecessary, and the tool is a simple two-parameter read-only poll. The expiry-on-URL and refund-on-failure notes cover the non-obvious behaviors an agent needs before calling.

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 50%: waitSeconds is documented in the schema (including the maximum of 50) while exportJobId has no description anywhere. The description's 'bounded waitSeconds' is consistent but adds no detail beyond the schema, and it never explains that exportJobId comes from export_mockup_animation.

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 mockup export progress and a short-lived download URL when complete'), which clearly distinguishes this status-polling tool from export_mockup_animation (starts the job) and get_mockup_animation (returns the artifact). It stops short of explicitly naming those siblings, so an agent must infer the boundary from the verbs.

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?

The polling intent is implied by 'progress ... when complete' and 'Supports a bounded waitSeconds', but the description never says when to call this versus get_mockup_animation or how often to retry. No exclusions or alternative-routing guidance are given.

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