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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description still adds real value by stating it does not consume credits and that the target must be owned and singular, which flags a likely failure mode for unowned or ambiguous IDs.

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 tight sentences with the capability first and the cost caveat second; nothing is redundant or padded.

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?

There is no output schema, and the description never says what an estimate looks like (credit amount, currency/units, per-setting breakdown). Combined with a completely undocumented nested parameter object, the definition leaves the agent guessing on both inputs and outputs for a pricing 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 description coverage is 0% and the single required parameter is a nested GenerationParameters object with nine undocumented fields (fps, detail, resolution, keep_color, upload_id, source_result_id, etc.). The description says nothing about which fields matter, that upload_id vs source_result_id select the target, or that settings affect the price. With zero schema coverage, this gap is costly.

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?

"Get server pricing for exactly one owned upload or result" states a specific verb (get), a specific resource (server pricing / estimate), and a cardinality constraint. It implicitly contrasts with generation-creating siblings via "Does not spend credits", though it never names an alternative.

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 phrase "Does not spend credits" implies the tool is a cheap pre-flight check before committing to a paid operation, and "exactly one" hints at a per-item call pattern. However, no explicit when-to-use statement, no named alternative (e.g. create_generation), and no prerequisites are given.

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