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

Annotations only say it is not read-only and is open-world; the description adds the human-in-the-loop flow (link is returned for the user to open, they record and press Stop) and that the change list arrives only via a separate get_change_list call that blocks. The remaining gap is whether record_screen itself waits for the user to finish and where exactly the job id is surfaced.

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?

Two sentences, front-loaded with the trigger condition before the mechanics and the follow-up call. The mechanics sentence packs several clauses together and could be broken up, but every clause carries information.

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 zero-parameter tool with no output schema, the description covers trigger, user flow, and required next call. It leaves the source of the job id implicit and does not state whether the call returns immediately or blocks until the recording ends, both of which matter for orchestration.

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?

The tool takes zero parameters, so the schema baseline applies; the description adds the useful framing that the real input is the user's spoken narration rather than any argument. Nothing further about inputs is needed.

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 action (spin up a screen recording session) and its concrete output (a recording link the user opens), plus the user-facing behavior 'they record their screen and talk through what should change, then press Stop'. The trigger condition quoted from the user ('let me show you', 'watch this') makes it immediately distinguishable from the conversion siblings.

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?

Explicit about when to use it: when the user wants to show rather than type, with concrete example phrasings and scenarios (bug repro, design/product review). It also names the mandatory follow-up step — call get_change_list with the job id — and warns that this follow-up waits for the user.

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