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

Adds substantial behavior beyond the annotations: renders are async and must be polled per task_id, quote_only avoids token deduction, target_fps=60 doubles token cost, batch is capped at 10 clips, and unreleased models cannot be started via MCP/API. These are non-obvious billing and workflow traits that annotations (readOnlyHint=false, openWorldHint=true) do not convey.

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-loads what the tool does and then packs workflow, pricing, and model guidance into dense sentences with no filler. It is information-heavy for a description but nearly every clause carries actionable detail; slightly more segmentation would help scanning.

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 9-parameter async, token-billed tool with no output schema, the description covers the critical loop (quote, confirm, submit, poll) and model availability constraints. It omits any description of what a status/render response looks like, but naming get_video_status for polling largely closes that gap.

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 100%, so baseline is 3, but the description adds real meaning: scale 1-4 with 1.5 allowed, target_fps range and its cost implication, Proteus as default model, accepted input forms for each clip, and that confirmed_quotes are ordered to match videos. Only minor ambiguity remains (e.g., behavior when both video and videos are supplied).

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+resource ('Upscale and enhance... videos with Topaz') and scopes it to the user's own videos or public https clips. An agent can distinguish it from generate_video, enhance_video_prompt, and the apply_* style tools without opening the 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?

Gives clear operating context: call list_upscalers first for model availability, use quote_only for exact prices, confirm via confirmed_quotes, reuse request_id on retries, and poll get_video_status for async renders. It never states when NOT to use this tool versus siblings such as enhance_video_prompt, so it stops short of full when/when-not guidance.

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