read_process_output

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

No annotations, so description carries full burden. It discloses incremental offset behavior, follow semantics (brief wait), stream behavior (pushes notifications/message and progress when progressToken provided), and return of next offset. This goes beyond basic 'read' and covers the most important behavioral nuances, though edge cases like invalid handles or binary output are not addressed.

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 sentences, front-loaded with the core purpose. Each sentence earns its place: primary read mechanism, follow/stream options, and stream selection plus return value. No redundant phrasing.

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 8 parameters and no output schema, the description covers the main workflow (offset-based reading, follow, stream, choosing stdout/stderr, return offset). It omits details on limit, binaryOutput, and streamMs, but these are optional and the overall operation is clear. Adequate for typical use.

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 63%, and the description adds meaning for follow, stream, which, and offset (via 'byte offset' and 'next offset'). However, it does not explain limit or binaryOutput, which are also missing from schema descriptions for limit and binaryOutput, leaving a gap for these parameters. Still, the key parameters are well covered.

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?

Description opens with a specific action and object: 'Read new output from a started process log, incrementally by byte offset.' This clearly distinguishes it from file-reading tools (read_file) and process-status tools (get_process_status) by focusing on process logs and incremental offset-based reading.

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?

Provides clear context: use after starting a process, with follow/stream modes. It explains how to use follow and stream and which stream to select. While it doesn't explicitly name alternatives or exclusions, the context is unambiguous and implies use for process output rather than file content.

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