snapshot_scrollback

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

With no annotations, the description discloses key behaviors: passive snapshot, no ingestion of new PTY bytes, and requirement for a session. It does not mention what happens if the session_id is invalid, any limits on scrollback size, or the return format.

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?

Three concise sentences. First sentence gives the main action, second provides prerequisite, third clarifies behavior. No 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?

Given no annotations, no output schema, and missing parameter details, the description is incomplete. It covers precondition and passiveness but lacks explanation of output shape and parameter semantics. Sibling tools like snapshot_screen are not differentiated beyond the passive note.

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 descriptions are missing (0% coverage). The description explains session_id's role indirectly but fails to explain the 'lines' parameter, which controls how many lines are returned. The default of 200 is not mentioned in the description.

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 retrieves 'rendered terminal scrollback,' a specific resource. It distinguishes itself from siblings like snapshot_screen (current screen) and clear_scrollback (destructive) by noting it is a passive snapshot.

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?

Explicitly states the precondition: 'Requires an existing session created via create_session(session_id, cwd).' It also notes the tool is passive and does not ingest new bytes, implying safe use. However, no explicit guidance on when not to use or alternatives.

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