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

Annotations only say readOnly/non-destructive/closed-world; the description adds real behavioral context by clarifying that 'build' means producing an in-memory scaffold and that no persistence, rendering, or publishing occurs, and that output is deterministic. It still omits what the returned deck looks like and whether validation errors are thrown for over-length copy.

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, the primary purpose front-loaded and the scoping caveat immediately after. Nothing 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?

With 8 undocumented parameters, no output schema, and four required fields, the description is too thin — it never says what the scaffold contains or how the agent should use it downstream. The safety profile is covered by annotations, but the functional contract is not.

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% across 8 parameters, including two enums and four required fields, and the description names none of them. 'Accepted copy' loosely gestures at hook/points/payoff but gives no guidance on length caps, point-count limits, or aspect ratios, leaving the schema to carry the entire burden.

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 ('Build a deterministic editorial carousel deck') plus its input source ('accepted copy'), which is materially more precise than the title. It does not name a sibling tool it should be preferred over, so an agent must infer placement relative to get_carousel_schema or scaffold_video_spec.

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 negative scoping ('does not render, save, or publish it') effectively excludes whole categories of misuse and implies this is a pre-render step. However, it never names the alternative to use for rendering/publishing, nor states the prerequisite tool that produces 'accepted copy' — the agent must infer the workflow position.

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