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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description still earns credit by adding the business-critical fact that nothing is charged ("without charging anything") and that the figure is exact rather than an upper bound. It stops short of describing error behavior for invalid arguments or what the response payload looks like.

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?

Two sentences, zero filler, with the scope and the no-charge guarantee front-loaded before the invocation instruction. Nothing could be removed without losing 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 a read-only estimator with a fully documented nested schema and no output schema, the description covers purpose, cost-free behavior, and argument convention. Only the return shape (a single number vs. a breakdown) is left unstated, which is a minor gap given there is no output schema.

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 100%, so baseline is 3; the description adds a genuine semantic layer by framing the nested video/ad objects as pass-through copies of the target tool's arguments, which tells the agent how the three-parameter shape maps onto create_video/create_ad/generate_hooks calls. It does not restate the kind enum semantics or note which fields actually affect price.

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?

"Returns the exact credit cost of a planned create_video, create_ad or generate_hooks call" states a specific verb (returns cost) and resource (credit cost), and names the three siblings it serves as a preflight for. An agent can distinguish it from create_video/create_ad 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?

"Pass the same arguments you would pass to that tool" gives concrete invocation guidance and implicitly defines the when: before running one of the three named generation tools. It does not explicitly say whether it is mandatory before generation or what to do if the estimate exceeds budget, but the context is clear.

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