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

With destructiveHint=true and readOnlyHint=false already declared, the description still adds real context: the original project is edited in place unless saveAsNewProject is true, the expensive operation is called out by cost, and the async nature is disclosed via the polling instruction. This is exactly the additional context annotations cannot carry.

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?

Four short sentences, zero filler, front-loaded with the core action and the mutation semantics before cost and polling details. Every sentence carries actionable information.

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?

An output schema exists so return values need not be described, and the description covers the remaining essentials: mutation semantics, cost tradeoff between edits, and the follow-up polling tool for async status. Nothing needed to invoke it safely is missing.

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 100%, and the schema already documents saveAsNewProject, projectId sourcing, and each edit enum value in detail. The description's parameter-related content (saveAsNewProject behavior, ZOOM vs CONVERT) largely repeats the schema, so baseline 3 applies.

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 ('Apply curated edits to an existing project') and immediately disambiguates scope from generic generation siblings by framing it as editing an existing project. The in-place-vs-copy behavior further pins down what kind of operation this is.

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 explicit selection guidance between edit modes: CONVERT_IMAGES_TO_VIDEOS is expensive, ZOOM is the cheap Ken Burns option, and it names list_project_remix_actions as the polling tool. It does not, however, say when to prefer remix_project over sibling generators like slideshow_to_video or generate_video_clip.

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