terminal_screen

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

With no annotations, the description carries the full burden and does well: it discloses VT emulation semantics (cursor moves, erases, color codes applied), the truncation strategy for max_chars (head+tail with an omission marker), and the return shape including running and exit_code state. It does not address whether reading is side-effect-free or how errors surface, but the core behavioral picture is solid.

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?

Front-loaded with the one-line purpose, then Args and Returns blocks that are easy to scan. Every sentence contributes, though the section scaffolding is slightly heavier than strictly necessary.

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?

No output schema exists, but the Returns block enumerates the fields (text, cursor, cols, rows, running, exit_code), and both parameters are documented. For a two-parameter read tool this is nearly complete, with only edge cases like reading a finished session left unaddressed.

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 0%, so the description must compensate, and it does: session_id is tied to 'Session returned by terminal_start', and max_chars is explained as a head+tail truncation with an omission marker, which is meaningful behavior beyond the bare schema default.

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?

States a specific verb and resource ('Return the rendered terminal screen (VT emulation) with cursor position') and the phrase 'This is the clean view' implicitly differentiates it from a raw-output sibling like terminal_read. However, it never names terminal_read, so the agent must infer the distinction rather than being routed 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?

Gives clear usage context: use it to see 'exactly what a human would see, including the current prompt or TUI', which tells the agent when a rendered view is preferable to raw bytes. There are no explicit exclusions and no named alternative, so it stops short of a 5.

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