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

Adds real context beyond the annotations: it spends AI credits, it can be refused for unrebuildable posts, and it advises passing idempotencyKey when the prior answer was never seen. It is consistent with destructiveHint=true and openWorldHint=true. It stops short of saying what happens to the original failed job's state or whether a retry is billed on refusal.

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?

The first two sentences describe the general Prolifik cloning feature rather than this tool specifically and even open with 'Paste a TikTok or Instagram link', which is not this tool's input (it takes a jobId). Tool-specific content is valuable but arrives after the domain preamble, so the most actionable sentences are not front-loaded.

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 a 2-parameter mutating tool with no output schema and no nested objects, the description covers the qualifying state, refusal cases, cost, and idempotency, which is enough to call it correctly. Minor gaps remain around the result of a successful retry and how the retried job is identified back to the caller.

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 50% because jobId carries no description; the prose compensates by implying jobId must reference a FAILED job with no variations. The idempotencyKey guidance in the description mirrors and slightly extends the schema text (retrying a call whose answer you never saw).

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+resource (re-runs a FAILED cloning job from the paste) and explicitly distinguishes itself from the sibling that handles the other case (add_clone_variations). An agent can tell retry_clone_job apart from clone_post, get_clone_job, and add_clone_variations without opening a 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?

Gives an explicit precondition (job must be FAILED and have no variations), two explicit exclusions (job already has variations -> use add_clone_variations; post the transform cannot rebuild -> refused), and a retry-safety rule for the idempotencyKey. This is textbook when/when-not guidance.

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