browser_start_recording

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

With no annotations, the description discloses several behavioral traits: the need to stop with browser_stop_recording, encoding via ffmpeg, and the real capture rate limitation. This provides good transparency, though it omits details on required permissions or side effects.

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 a single paragraph with multiple sentences, each adding relevant information. It front-loads the main action and is efficient, though slightly verbose with technical details. No wasted words, but could be more concise regarding parameter semantics.

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?

The description covers the main action, complementary tool, encoding details, and a use case. However, it lacks explanation of the session_id parameter and does not clearly differentiate from similar tools like browser_screenshot. Given the presence of an output schema, return values need not be explained, but overall completeness is adequate.

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 0% and the description only explains the fps parameter (frames per second). The session_id parameter is entirely undocumented, leaving its purpose unclear. The description adds minimal semantic value beyond what the schema provides for one of two parameters.

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 tool starts a screen recording and captures viewport frames at a specified fps. It distinguishes from siblings by referencing the complementary stop tool and noting that Camoufox cannot write native video, making the tool's purpose unambiguous.

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 usage for recording demos by mentioning it's great for README/marketing demos and noting a limitation on capture rate. However, it does not explicitly contrast with alternatives like browser_screenshot or browser_start_tracing, or state when not to use this tool.

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