process_write

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

Annotations already signal destructive/mutating behavior (destructiveHint=true, readOnlyHint=false). The description adds valuable stateful context beyond annotation:s recovered processes remain inspectable but their stdin cannot be reattached, which is exactly the kind of limitation an agent needs to avoid calling this tool in the wrong situation.

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?

Two concise sentences: the first states the core action and target, the second adds a critical limitation. No wasted words, and the most important information is front-loaded.

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 simple stdin-writing tool, the description plus annotations and complete parameter schema cover what an agent needs to invoke it correctly: the PID source, the input content, the optional `end` flag, and the recovered-process limitation. It does not describe return values or error cases, but no output schema is declared and those are not essential for this operation.

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 100%, so the schema already documents `pid`, `input`, and `end` fully. The description reinforces that `pid` must come from start_process and that `input` is UTF-8 text, but it adds little new semantic detail beyond the schema. This matches the baseline for high schema coverage.

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 ('Write'), a precise target ('standard input of a live process started by start_process'), and the content type ('UTF-8 text'). This clearly separates it from sibling tools like read_process_output and stop_process.

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 phrase 'live process started by start_process' establishes when the tool should be used, and the recovered-process sentence gives an explicit exclusion: stdin cannot be reattached after restart. It does not name an alternative tool, but the process-management sibling set makes the intended context clear.

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