wait_for_output

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

Because no annotations are provided, the description itself must disclose how the tool behaves, and it does: the existing snapshot is searched first, then it polls until timeout. It also explains regex versus literal matching. It does not describe error behavior when timeout elapses or how recent-unwrapped differs from recent, which is a mild transparency gap.

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 description is compact, front-loaded with the main behavior, and each line adds a meaningful piece of information for a parameter or option. There is no redundant or filler wording.

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?

For a polling/search tool with an output schema and five parameters, the description covers purpose, pattern semantics, source selection, search order, and timeout. The main residual gap is the meaning of recent-unwrapped and what happens when the wait times out, but nothing blocks a competent agent from selecting and invoking the tool correctly.

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?

The input schema provides property names and defaults but no descriptions, so coverage is 0%. The description compensates by explaining pane id format, pattern semantics, regex behavior, source choices, and timeout usage. The timeout_ms explanation is thinner than the others, relying on the schema default for full meaning, so it is useful but not complete.

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 opens with a specific verb and resource: wait for a pane's output to match a pattern. It clearly communicates the tool's synchronous, polling nature and distinguishes it from siblings like read_pane, which would only inspect the current snapshot, and wait_agent, which waits on an agent rather than a pane.

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 gives practical usage context, including the order of operations, expected pattern syntax, source options, and timeout behavior. It does not explicitly name alternatives like read_pane or wait_agent for contrast, so it stops short of full when-to-use/when-not-to-use guidance, but an agent can infer the right situation clearly.

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