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

Annotations already convey the operation is not read-only, not idempotent, and destructive (destructiveHint=true). The description adds the crucial fact that the operation is paid and involves settlement+enqueue, which annotations cannot express. It does not explain what destructive side effects occur or what 'settle' means.

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?

The description is admirably brief and front-loaded with the endpoint and action; no filler. The cryptic 'settle+enqueue' reduces clarity, but every sentence carries intent and the routing preference.

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?

A six-parameter paid queue operation with no output schema needs far more context: what settlement means, preconditions, cost implications, and parameter meaning. The one-line description plus sparse annotations is inadequate.

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 17% (model alone is documented), and the description adds no parameter information. With six parameters and no enums, an agent has no guidance on prompt semantics, duration, resolution, aspect_ratio, or audio from either the schema or the description.

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?

The description explicitly identifies the endpoint and core action ('paid settle+enqueue'), and it points to generate_video as the preferred alternative, which helps distinguish it from sibling tools. However, 'settle+enqueue' is jargon and does not fully specify the tool's purpose or effects.

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?

It provides one explicit routing cue: 'Prefer generate_video for agents,' which tells an agent that this is not the default choice. It does not specify what conditions would warrant using video_queue over generate_video, video_quote, or video_complete, so the guidance is partial.

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