Capture the TV screen and save it as a PNG so you can see which item the remote is on before pressing select.
Capture what the TV is showing and save it as a PNG on this machine.
Use it to see which item the remote is sitting on before pressing select.
| Name | Required | Description | Default |
|---|---|---|---|
| save_path | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does disclose the key behavioral trait that the output is a PNG written to the local machine rather than returned inline. However, it says nothing about prerequisites (TV pairing/connection), latency, failure modes if the TV is unreachable, or how save_path defaults behave — significant omissions for a device-capture tool with zero annotation coverage.
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 short sentences, zero filler, and the primary action is front-loaded ahead of the secondary usage hint. 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?
An output schema exists, so return values need no explanation, and for a one-parameter read-only capture tool the description covers purpose and intent adequately. It is still missing device-prerequisite context and save_path behavior, which leaves it minimally viable rather than complete.
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% for the single save_path parameter, so the description must compensate. It hints at local saving ('save it as a PNG on this machine') but never names save_path, explains its format, or clarifies what the empty default means (temp dir? current dir?). That gives only partial compensation for a total documentation 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 verb and resource ('Capture what the TV is showing') plus the output artifact ('save it as a PNG on this machine'), which is materially different from siblings like tv_status or tv_control. It implicitly distinguishes itself from status/control tools but never names or contrasts them explicitly, keeping it below a 5.
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?
Gives a concrete when-to-use scenario: 'see which item the remote is sitting on before pressing select,' which tells the agent this is a visual-verification step preceding tv_control. It offers no exclusions or named alternatives (e.g., tv_status for non-visual checks), so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.