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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the description isn't required to restate those. It adds genuinely useful behavioral context: the marker lands on the active recording, t_ms is elapsed ms since recording start, note becomes a caption source, and the tool returns no_active_session if nothing is recording. It also discloses the surprising session_id behavior (accepted and ignored) in the schema, which is a notable behavioral trait.

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 sentences with zero waste. The core action is front-loaded, the key timing parameter is defined immediately, the optional bounds behavior is stated compactly, and the error return is disclosed. Every sentence earns its place.

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 tool with 4 parameters, 100% schema coverage, and no output schema, the description covers the essential context: what the marker is, how timing works, how bounds work, and the failure mode. It doesn't describe the return value on success, but with no output schema and a simple marker-drop operation, that's a minor gap. The session_id quirk is documented in the schema, which is the right place.

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 description coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining the semantics of t_ms (elapsed ms since recording start) and bounds (global points, top-left, zoom toward an element, omit for full-frame). The session_id parameter's 'accepted and IGNORED' behavior is also explained in the schema, which is valuable. The description doesn't add much beyond the schema, but the schema itself is already rich.

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 states a specific verb ('Drops'), a specific resource ('a named marker into the active recording's timeline'), and the key timing parameter (t_ms). It clearly distinguishes this from sibling tools like screen_record_start/stop/status and video_* tools by focusing on timeline annotation rather than capture or post-processing.

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 explains when to use it (during an active recording) and what the bounds parameter is for ('zoom toward an element, or omit for full-frame'). It doesn't explicitly name alternatives or say when not to use it, but the context of 'active recording' plus the sibling set makes the usage context clear.

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