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

Annotations declare a non-read-only, non-idempotent, non-destructive local operation, and the description adds genuinely new context: the call may or may not start work immediately depending on balance, and in the checkout case it returns a URL that the user must open before the restore begins. It does not warn about double-invocation behavior despite idempotentHint=false.

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 dense sentence with the precondition front-loaded and the two outcome branches clearly parallel. No filler, no repetition of the title.

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 usefully explains the key return value (checkout_url) and what triggers it. It leaves the successful balance-paid response shape and post-start polling guidance (e.g., get_restore) unstated, which is a minor gap for a job-launching tool.

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_id is already documented in the schema as the value create_restore returned (cloud_…). The description adds no format, prefix, or validation detail beyond that, so the 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?

States a specific verb and resource ("starts a restore") and distinguishes two distinct execution modes: balance-paid (immediate) and checkout (returns checkout_url, starts after payment). The precondition "After the video is uploaded" also positions it in the workflow relative to create_restore, though no sibling is named outright.

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?

Clearly signals when to call it (after upload / after create_restore produced the job_id) and explains the branch that determines whether money is collected up front. It does not state any exclusions or name alternatives such as quote_restore for pricing, so it stops short of full routing guidance.

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