Read terminal output

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

Annotations already declare readOnlyHint=true, covering the read-only nature. The description adds the cursor-based semantics and that it returns the new cursor, which is valuable. However, it does not disclose whether the call is blocking (e.g., waits for output) or how it handles no new output. Given the existence of terminal_wait, this is a notable gap, but not a contradiction. The description adds some behavioral context beyond annotations but leaves key behaviors unspecified.

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 short sentences, front-loaded with the core action and cursor semantics. It is free of filler and effectively communicates the main purpose. The structure is optimal for quick agent comprehension.

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?

The tool has an output schema (which presumably describes the return value including the new cursor), so return values are covered. However, the parameters are not explained, and the description does not mention any edge cases (e.g., no new output, limit reached). The context is adequate for a simple read tool but incomplete given the undocumented parameters and the presence of a wait sibling that could clarify blocking behavior.

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 description coverage is 0%, so the description must explain the parameters. It only implicitly references 'cursor' in the phrase 'since cursor' but does not explain what limit, cursor, or session_id mean. It does not clarify that cursor is a token representing the last read position, that limit caps output size, or that session_id identifies the terminal session. This is insufficient for a tool with three parameters and no 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 reads new output from a terminal session since a cursor and returns the new cursor. It specifies the resource (terminal output) and the action (read), and it distinguishes itself from siblings like terminal_write and terminal_wait by focusing on reading output. The cursor-based incremental reading is a clear differentiator.

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 implies usage: read output after writing or waiting, but it does not explicitly state when to prefer this tool over alternatives like terminal_wait or terminal_list. It gives the context of reading 'new output since cursor' but lacks any explicit exclusions or comparisons to sibling tools. An agent would need to infer that this is the non-blocking read tool, which is not stated.

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