Startrecording

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

With no annotations, the description carries the full burden and does so well: it discloses display selection from the agent's own process tree, that another session's display is never used, the exact defaults, the behavior when maxDurationSeconds is reached (capture stops, file retained for finishRecording), and the no-duplicate-recorder semantics. This is rich behavioral context beyond what any structured field provides.

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 paragraphs, front-loaded with the action and the timing rule, then escalating to edge-case behavior. Every sentence adds information an agent needs; nothing is padded or repeated.

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 explained. Given two optional parameters, no annotations, and a set of closely related sibling tools, the description covers timing, defaults, cross-session safety, duration-limit handling, and idempotency — everything needed to invoke it 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 coverage is 0% and the schema only lists bare types with defaults, so the description must compensate. It supplies the default values and, more usefully, the consequence of maxDurationSeconds being reached, though it never explains what fps controls or states any valid range for either parameter.

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 ('start recording the agent computer display') and scopes it to browser/computer-use actions, which cleanly separates it from finishRecording, abortRecording, recordingStatus, and cleanupRecording. An agent can identify the tool without opening the schema.

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 timing guidance: 'Call this before the first browser or computer action,' plus the when-not case that an already-active or pending recording is returned instead of starting a second one. It does not name sibling alternatives for the status/finish/abort flows, so routing is implied rather than spelled out.

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