tv_ui_record

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

No annotations are provided, so the description carries the burden. It discloses meaningful constraints: a 1-20 step cap, single-capture semantics, and prohibited content categories. It omits failure behavior, whether the recording is persisted, and any auth/prerequisite needs.

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 tight sentences, front-loaded with the core action and followed by constraints and exclusions. Dense but no filler, though the shorthand ('Inspect then tv_learn') borders on cryptic.

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 return values need no explanation, and the description covers the key behavioral constraints. But for a 5-parameter tool with 0% schema coverage and no annotations, the parameter layer remains substantially unexplained.

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% across 5 params (4 required), and the description only touches one of them ('text $VALUE parameterizes the route'). name, from_state, to_state, and steps receive no explanation of format or meaning, so the description fails to compensate for the coverage gap.

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: run 1-20 press/wait/text/replace_text/submit steps from an anchored state and capture the result once. The 'record/capture once' framing distinguishes it from a plain step-runner sibling like tv_ui_run, though it leans on jargon ('anchored state') the agent must resolve elsewhere.

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?

Provides explicit when-not guidance ('Never learn loading as completed content, nor purchases, account edits or consent routes') and a workflow hook ('Inspect then tv_learn'). It does not, however, explain how to choose this over tv_ui_run or tv_learn directly.

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