qt_record_start

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

With no annotations, the description carries the full burden and does disclose useful traits: recording runs in the background, returns a recording id encoding the app, and auto-stops after max_seconds. It omits where the GIF is written, whether a second concurrent start is allowed, and what happens if the process ends before stop is called.

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 short sentences, front-loaded with the action and its companion tool, then the return value, then the auto-stop guard. Nothing is wasted.

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?

With 13 parameters, zero schema descriptions, and no annotations, the brief lifecycle note is not enough to call the tool correctly — an agent cannot tell what the widget-selection parameters do or how they interact. The output schema covers the return value, so that gap is fine, but the input side is severely under-explained.

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?

13 parameters at 0% schema description coverage, and the description explicitly explains only max_seconds (and obliquely instance). fps, ref, index, expand, describe, max_width, min_score, class_name, object_name, window_title and search_fields are entirely undocumented in both places.

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 a background GIF recording', with 'background' signaling the asynchronous variant. It names qt_record_stop as the terminator but never contrasts itself with the sibling qt_record_gif, leaving the start-vs-record_gif choice to inference.

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?

It clearly gives the lifecycle: call this, then qt_record_stop, and it self-terminates after max_seconds. However it never says when to pick this over qt_record_gif, nor any prerequisites about targeting an application instance before starting.

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