Computer Teach Step

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

With no annotations, the description carries the full burden and does the most important part: it discloses that this is a stub, that the only real effect is recording the human's intent, and that it returns guidance text rather than performing playback. It stops short of saying whether that record persists, is scoped per session, or has any side effect on subsequent computer_* calls.

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 'stub scaffold' caveat and the redirect to computer_batch, with no filler. Slightly dense parenthetical phrasing but every sentence 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?

An output schema exists, so the returned guidance text needs no further explanation, and the stub status is clearly flagged. However, with no annotations and an undocumented 'instruction' parameter, an agent still cannot tell what to put in the argument or whether the call changes any persistent state.

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 0% and the single required parameter, 'instruction', is never explained in the description — no guidance on whether it is a natural-language description of the demo, a step label, or free-form notes. For a 1-param tool this is the one place the description needed to compensate and it does not.

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 object: it records that the HUMAN intends to demo an action for the agent to repeat, and it self-identifies as a 'stub scaffold' rather than a real recorder. It also names a sibling (computer_batch) that covers the real repeatable-sequence need today, so an agent can separate it from the click/type/key automation tools.

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?

Explicitly gives the when ('the HUMAN wants to demo an action'), the when-not (full playback recording is not implemented yet), and the alternative ('use computer_batch scripts for repeatable sequences today'). Nothing about tool selection is left to inference.

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