screencast_start

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

Annotations only provide readOnlyHint=false. The description adds concurrency info (multiple recordings allowed) and that output is saved to downloads. However, it does not disclose limitations, permission needs, or behavior on failure. Sufficient but not rich.

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?

Two sentences, concise, front-loaded with primary action. No redundant or unnecessary 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?

Given no output schema, the description explains the return value (id). It covers the core functionality, concurrency, and destination (downloads). Missing details like file naming or size limits, but complete enough for typical use.

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 covers 100% of parameters with descriptions, so the baseline is 3. The tool description does not add extra parameter details beyond the schema, but it does mention that the returned id is used with screencast_stop, which is helpful context.

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 the verb 'Start recording' and the resource 'screencast of the current page viewport'. It also explains the output (file in downloads, returns id) and distinguishes from sibling tools like screenshot_page and screencast_stop.

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 implies when to use (recording video of viewport) and mentions multiple recordings can run at once, but does not explicitly state when not to use or name alternatives. The context is clear enough for an agent to decide.

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