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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely non-derivable behavior: it is asynchronous and must be polled via get_clone_job, it consumes AI credits, and idempotencyKey should be passed on retries. It stops short of describing failure/partial-success behavior, so not a 5.

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?

Front-loaded with the core action and the cost/comparison rationale, then the async and credit/idempotency caveats. The opening 'Paste a TikTok or Instagram link' sentence is slightly puzzling since no URL parameter exists (jobId is passed), but overall every sentence carries information.

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 async, credit-spending mutation with no output schema, the description covers the important agent-facing facts: polling target, cost, idempotency, and lifecycle ('stay on the cloning job until saved to the Library or scheduled'). Minor gap: it doesn't reconcile the 'paste a link' framing with the jobId parameter the agent actually supplies.

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 only 33%, with jobId and variations undocumented structurally. The description implies the job context (an already-analysed cloning job) and explains idempotencyKey usage, partially compensating, but it never clarifies jobId semantics or the variations count beyond the schema's 1–8 range. Baseline 3 given partial schema coverage plus marginal added meaning.

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 (add/build) and resource (variations on a cloning job), and immediately distinguishes scope from a fresh clone ('cheaper than a new clone, because the post is downloaded and read only once'). An agent can tell this apart from clone_post and localize_clone_variations 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?

Gives clear when-to-use context: it operates on a job that is already analysed, and contrasts that with creating a new clone. It also states the async workflow (poll get_clone_job) and the retry condition for idempotencyKey. It does not explicitly name sibling alternatives like localize_clone_variations, so it falls short of a 5.

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