tmux_capture

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

There are no annotations at all, so the description carries the full burden of behavioral disclosure. It does disclose the core behavior — grabbing the most recent `lines` of the current pane output, bounded to 10–2000 — but it never explicitly states that the operation is read-only/side-effect-free, nor does it address behavior for missing sessions or out-of-range values.

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?

The three short sentences are all informative and free of filler: the first states the action and scope, the second gives the motivating use case, and the third conveys a parameter constraint. The key scoping information is front-loaded immediately.

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?

The tool has only two parameters (one required) and an output schema, so the bar is modest. Even so, given complete absence of annotations, the description omits useful context: what happens when a session doesn't exist, whether the operation is indeed read-only, and why it should be chosen over siblings like tmux_status or read_log. It's usable but not fully self-contained.

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, and it partially does: it clarifies that `session` refers to the tmux session whose pane is captured, and it adds a critical constraint for `lines` (valid range 10–2000) that the schema does not express. This is genuine value-add beyond the raw integer type.

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 states a specific action — 'capture the current pane output of a named tmux session (back `lines` lines)' — with a clear verb and resource. It also gives a concrete use case (viewing live service logs like ego-planner/agent_run) that implicitly separates it from siblings such as tmux_status or read_log, though it never names those alternatives explicitly.

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 description clearly identifies the scenario when the tool is appropriate: to inspect continuous logs that a service writes to a tmux pane. It does not, however, state when not to use it or contrast it with the alike siblings (e.g., using read_log for file-based logs or tmux_status for session status checks), so explicit exclusions are missing.

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