browser_teach_start

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

With no annotations, the description carries the load well: it discloses that recording happens in the agent's Chrome with human interaction, that the session ends via a banner button, that selectors are stored by accessibility role/name rather than pixels, and that passwords are never captured. It omits what happens if a session is already running and what permissions or side effects apply to the page.

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?

Front-loaded with the mode label, then the workflow, then storage guarantees, then the next call — a logical order with little waste. A couple of clauses (element storage, passwords) are adjacent rather than integrated, but nothing is padding.

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 two-parameter session-start tool with no output schema, the description covers trigger, human interaction model, termination signal, selector strategy, and a security guarantee. Missing only edge cases such as an already-active recording or how to abort without recording.

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 both url and name are already documented in the schema; baseline 3 applies. The description adds no extra detail about the name format or URL expectations beyond the schema's own "buscar-factura" example.

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?

Starts with a mode label ("MODO ENSEÑAR") and a specific verb+resource: start recording a recipe where the human performs the task once in the agent's Chrome. It is clearly separable from browser_teach_stop (the closing step) and from browser_record_start, which it does not overlap with in wording.

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 states the operating procedure (the person performs the task once, then presses "Terminar" in the banner) and names the mandatory follow-up call to browser_teach_stop. It does not explicitly exclude browser_record_start as an alternative, which keeps it from a 5.

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