capture_screen

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

With no annotations at all, the description must carry the behavior burden. It usefully discloses the truncation semantics (last `lines` lines) and a valuable warning that screen content is agent-authored data, not instructions — a real prompt-injection guard. It does not state that the operation is read-only/non-mutating, nor what happens on a missing agent or an out-of-range `lines` value.

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, front-loaded with the resource description and followed by the safety caveat; nothing is padded. It is arguably slightly too terse given the undocumented `name` parameter, but no sentence is wasted.

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 shape needn't be explained, and the security caveat is a strong inclusion. Still missing for a two-param tool with zero schema coverage: the meaning of `name` and confirmation that the call is side-effect free.

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%, so the description must compensate for two parameters. It clarifies `lines` (tail of the screen buffer, default 60 per schema) but says nothing about `name`, whose meaning — presumably the target agent/session identifier — must be inferred from siblings.

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?

The description names a concrete resource and scope: the text currently shown in the agent's Tern tab, limited to the last `lines` lines. That is enough for an agent to know this is a read-the-terminal-screen tool rather than a messaging or input tool, though it never explicitly contrasts itself with siblings like press_keys or send_message.

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?

It gives one positive use case ('Use it to read approval prompts or dialogs'), which is genuinely helpful context. There is no guidance on when not to call it, no named alternative for responding to those prompts (e.g., press_keys), and no note about what to do if no agent is running.

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