screencast_start

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

Beyond annotations (readOnlyHint=false), description adds that recording saves to a file, returns an ID, and supports multiple concurrent recordings. Does not mention potential performance impact or file overwrites.

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?

Three concise sentences, each providing essential information: action, output, ID usage, concurrency. No redundant text.

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?

Given no output schema, description adequately states return type. Parameters are fully covered in schema. Could mention file naming or overwrite behavior but not required.

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 3. Description does not add meaning beyond schema; it only implies viewport-related defaults but doesn't elaborate on parameter usage.

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 clearly states it starts recording a screencast of the viewport, saving to a file, and returns an ID. It distinguishes from sibling tools like screenshot_page (static image) and screencast_stop (stops recording).

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?

Explicitly mentions saving to downloads, returning an ID for stopping, and that multiple recordings can run at once. Does not explicitly state when not to use (e.g., for static screenshots), but sibling tools imply alternatives.

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