Read pane output

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so thoroughly. It reveals that transcript mode reads from disk (not screen), screen mode avoids overdraw/spinner spam, waitForIdle blocks with configurable timeouts, since acts as a byte cursor, and every read returns the current cursor. No contradictions with annotations exist.

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 a single dense paragraph of roughly 180 words. It is front-loaded with the primary purpose, and every sentence adds operational value for a 9-parameter tool with three modes. It is somewhat lengthy, but the complexity justifies the detail; no waste is present.

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 tool with 9 parameters, no output schema, and only 67% schema parameter coverage, the description covers all significant behavioral facets: mode semantics, cursor-based incremental reads, blocking waitForIdle behavior, defaults for settleMs/timeoutMs, and an explicit streaming alternative. It is complete enough for an agent to select and invoke 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?

Schema coverage is 67%, leaving tail, strip, and paneId without schema descriptions. The description compensates by explaining tail ('limits to the last N lines'), strip ('removes ANSI escape codes'), and adding rich context for mode, since, and waitForIdle. However, messages and paneId are not addressed in the description, though schema covers messages and paneId is self-evident.

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 the specific action 'Read a pane's terminal output' and then details three distinct modes (raw, screen, transcript), clarifying what each returns. It explicitly contrasts with the raw pty stream and screen scraping, and the sibling set includes read_messages, so the purpose is clearly distinguished from alternatives.

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 provides explicit usage guidance: mode:"transcript" is called 'the reliable way to read a claude pane', waitForIdle is 'the way to read a reply without polling/sleeping', and it directs users to 'subscribe to the pane's output resource instead' for continuous streaming. This clearly states when to use this tool and when to use an alternative.

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