terminal_snapshot

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

The description discloses that the tool provides a point-in-time snapshot rather than a continuous log, and that it includes scrollback. The annotations already cover read-only and idempotent behavior, so the description adds the key distinction from terminal_read without contradicting annotations.

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 two concise sentences, front-loaded with the core action and quickly clarifying the alternative and prerequisite. No filler or redundant information.

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?

With an output schema covering return values, annotations covering safety, and the description covering the core behavior and distinction from terminal_read, the tool is sufficiently complete for the agent to select and invoke it correctly. Minor gaps in parameter-specific details are handled by parameter semantics scoring.

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 schema has no descriptions (0% coverage), and the description only mentions that lease_id is required, which is already in the schema. It does not explain the roles of alias, pane_id, or include_history beyond the general scrollback mention, failing to compensate for the missing schema descriptions.

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 clearly states the tool captures a visible pane and scrollback via capture-pane, with a specific verb and resource. It also distinguishes itself from terminal_read by stating it is not an incremental log, making its purpose unambiguous.

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 explicitly says not to use it for incremental logs and directs to terminal_read instead, providing a clear alternative. It also notes the lease_id requirement, implying it is for active terminal sessions. This gives clear when-to-use and when-not-to-use guidance.

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