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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds valuable behavioral context: the headless browser opens the URL, holds the top, smooth-scrolls to the bottom, captures silently, and shows the public page. It also discloses that the capture is silent and public, which is important for agent expectations. It doesn't contradict annotations.

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 dense but front-loaded with the core purpose and scoping. It packs a lot of behavioral detail into a few sentences, though the all-caps emphasis and slightly run-on structure reduce readability slightly.

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 tool with no output schema, the description covers the key behavioral aspects: what happens during capture, defaults, constraints, and how to place the result. It doesn't describe the return value format, but the description's placement guidance and behavioral detail make it largely complete for an agent to invoke correctly.

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 20%, so the description must compensate. It explains duration_s (4-30, default 12), orientation (defaults to project's output frame), scroll (false just holds the top), and project_id (immutable scope, never guessed from active-project pointer). This adds meaning beyond the bare schema types.

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 states a specific verb and resource: 'RECORD A LIVE WEB PAGE as video' with a headless browser, and distinguishes it from siblings like download_url, fetch_url, and record_website_demo. It clearly identifies the tool's purpose and scope.

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 description explicitly says this is THE tool for 'show my website / landing page / this product page in the edit', and notes it is SILENT and shows the PUBLIC page (no logins, no clicks), which tells the agent when not to use it. It also mentions placement with insert_media or add_overlay(fit='cover'), providing clear context for use.

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