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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered structurally. The description adds the triggering scenario but does not disclose the behavior that matters here: that the input is consumed irreversibly, what happens if the process isn't actually waiting, or how timeout_ms interacts with the wait.

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 short sentence with no filler, and the triggering condition is front-loaded where the agent will read it. Nothing to cut.

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?

An output schema exists so return values need no explanation, and annotations cover safety. However, with four process-related siblings in the list (start_process, read_process_output, wait_for_process_output, kill_process), the description omits the prerequisite that the pid must come from start_process and gives no guidance on choosing between this and wait_for_process_output.

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 pid, input, device and timeout_ms are all documented in the schema itself. The description contributes no additional parameter meaning, so the baseline of 3 for fully-covered params is correct.

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 is framed entirely as a trigger condition ('when a running process is waiting for input') rather than stating what the tool does. Combined with the name and the schema (pid + input line), an agent can infer it sends a line of input to a process's stdin, but the description itself never supplies the verb+resource. It does at least distinguish the scenario from starting or killing a 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 when-to-use condition is explicit and concrete: a running process blocked on a prompt or confirmation. It stops short of 5 because it names no alternative and no exclusions — nothing routes the agent between this tool and the closely related siblings wait_for_process_output or read_process_output.

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