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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the mutation risk is covered structurally. The description adds the useful fact that output typed is echoed back as printed text, but says nothing about how waiting works beyond the schema, whether the process can die mid-call, or that the interaction is stateful/irreversible.

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?

A single front-loaded sentence with no filler; the core action comes first and the parenthetical hint is short and actionable.

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 input-passthrough tool with no output schema and annotations covering the safety profile, the description is nearly sufficient. It only lacks a note on blocking duration/timeout semantics, which wait_ms in the schema partially covers.

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 75%, so the schema documents pid, device and wait_ms; the description adds the one thing the schema omits for 'input' – that appending a newline acts as pressing Enter. That is meaningful semantics beyond the structured fields.

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?

Names a specific verb (type text into) and resource (a process started with start_process), and the phrase 'return what it prints next' implicitly separates it from read_process_output. Sibling differentiation is present but not spelled out by name.

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?

It establishes the prerequisite that the process must come from start_process and explains the newline-to-Enter convention, which is genuine usage guidance. It never states when to prefer this over read_process_output or what to do if the process is no longer running.

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