Skip to main content
Glama

rex_capture

Capture the screen and scrollback of a terminal block to inspect output; defaults to the focused block in the session's default window if no block is given.

Instructions

Screen and scrollback of a terminal block. Without block, the focused block of the session's default window.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "rex_capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
blockNoBlock label, ID, or ID suffix
formatNo
unwrapNo
sessionNoSession label or ID
max_bytesNoDefault 200000; truncated from the front
tail_linesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

No annotations are supplied, so the description must carry the behavioral load; it discloses what content is returned and how the target block is resolved by default, which implies a read-only capture. It says nothing about whether capture disturbs terminal state, error behavior for a missing or ambiguous block, or cost/size limits beyond the schema's max_bytes default.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core purpose front-loaded and the fallback rule immediately after; nothing is padded. It is terse to the point of leaving gaps, but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six optional parameters, no annotations, and no output schema, an agent still cannot tell what the capture returns in each `format` mode, what `unwrap` changes, how `tail_lines` interacts with `max_bytes`, or whether output is paginated. The description covers only the targeting fallback, leaving the tool's core output contract underspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%. The description adds genuine meaning for `block` by explaining that omitting it falls back to the focused block of the default window, which the schema does not state. However, `format` (text/html/vt), `unwrap`, and `tail_lines` get no explanation anywhere, so half the parameters remain semantically opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource and the exact content returned: the screen and scrollback of a terminal block. That is concrete enough to distinguish it from control-plane siblings like rex_send_keys or rex_block_close, but it never contrasts itself with the closest read siblings (rex_block_info, rex_session_view), so the boundary is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only guidance is a default-resolution rule: with no `block`, it captures the focused block of the session's default window. That tells an agent how to call it minimally but not when to prefer it over rex_block_info or rex_session_view, and gives no when-not-to-use conditions.

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