Add a marker

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

Annotations establish this is a non-destructive, non-idempotent write. The description adds real behavioral value beyond them: timing is on the video clock, pauses are excluded, and markers surface via stop_recording as {atMs, label}. It omits failure modes (e.g., calling when no recording is running) and the 200-char limit.

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?

A single dense sentence that front-loads the action and folds timing semantics and return-value behavior in without waste.

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 one-parameter tool with no output schema, the description covers purpose, timing semantics, and where the result surfaces (stop_recording output), which is everything an agent needs to call 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 100%, so label is documented, but the description still adds meaning with concrete examples ("signed in", "error shown") that convey the expected brevity and granularity better than the schema's "in a few words."

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?

Specific verb plus resource: "Mark this moment of the running recording with a short label." It clearly differentiates from the recording-control siblings (start/pause/resume/stop_recording) by being an annotation action during an active 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?

The phrase "the running recording" implies it applies only while a recording is active, and the note that stop_recording returns markers clarifies downstream usage. It stops short of explicitly stating when not to use it or naming an alternative for post-hoc annotation.

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