tv_learn

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

With no annotations, the description carries the full burden. It implies a persistent side effect (creating a reusable addon) but does not say whether the addon is actually saved, where, whether it is reversible, or what permissions/state the witness_id must satisfy. Only the 'visually verified first' precondition is disclosed.

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, no filler, with the precondition front-loaded before the action. Efficient, though the second sentence's guidance is bolted on rather than structured.

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 no-annotation, no-output-schema tool with 0% parameter coverage and an apparent write/persistence effect, the description leaves major gaps: what a 'route' or 'addon' is, what witness_id references, and what the result looks like.

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 coverage is 0%, so the description must compensate. It usefully constrains 'notes' (record what the image actually proved) but leaves 'witness_id' entirely unexplained in both schema and description, so half the parameters remain opaque.

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 verb ('compile') and an artifact ('reusable addon') but relies on unexplained jargon ('route', 'addon') that the agent cannot map to a concrete output. It is distinguishable from siblings like tv_observe or tv_discover by the learning/persistence framing, but the actual effect remains fuzzy.

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 opening clause gives a sequencing precondition: run this after visually verifying the latest native action or UI recording screenshot. That is real when-to-use guidance, but no alternatives are named and no case is given for when not to learn a route.

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