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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false, but the description adds the crucial non-annotation fact that each call consumes one order credit, plus the confirm-intent-first caution appropriate to a costly, non-idempotent operation. It does not address whether a credit is refunded on failure or whether the creation is reversible, which would be the remaining valuable disclosures.

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 action and its cost, then the input contract, then the mode menu. Dense but every sentence carries operational content; the workflow sentence is long yet earns its space by disambiguating the enum values.

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 7-parameter, nested, credit-spending mutation with no output schema, the description never states what comes back (a production id?) or what the next step is in the pipeline (storyboard review/approval). An agent can invoke it correctly but cannot reliably chain following calls from this text alone.

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 57%, and the description compensates by explaining the productUrl-vs-manual mutual exclusivity (which the schema does not encode via oneOf) and the three accepted photo source forms with the 1–8 bound. It omits language and clientRequestId, though the schema documents both adequately.

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 new production') and immediately adds the material consequence ('spends one order credit'). The workflow enumeration (showroom/influencer/viral) with one-line characterizations lets an agent distinguish the three creation modes without opening the schema, and the name is clearly separable from list_productions, get_production, or approve_storyboard.

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?

Provides clear operational context: supply productUrl OR manual+photos, pick a workflow, use brief for tone/audience/claims, and 'Confirm the person's intent first' as a prerequisite before spending credit. It does not explicitly say when NOT to use it or name sibling alternatives (e.g., that follow-up steps go through approve_storyboard or wait_for_production), 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.