Start process

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

Annotations already declare non-readonly, destructive, and closed-world semantics, so the safety profile is covered. The description usefully adds that the process is persistent and returns a PID plus initial output/state, but omits timeout behavior, the fact that started processes must be explicitly terminated, and any auth/permission context.

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 verb, resource, and key return values come first. It is efficient, though arguably too terse for a seven-parameter tool.

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 7-parameter, destructive, session-creating tool with no output schema and no schema descriptions, the description leaves major gaps: no parameter meaning, no timeout/cwd/shell semantics, and no lifecycle guidance. Only the bare purpose is conveyed.

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?

The schema has 0% description coverage across 7 parameters and the description explains none of them. Meaning for cwd, shell, deviceId, deviceName, timeout_ms, and verbose_timing is absent from both schema and description, so the required compensation for low coverage is entirely missing.

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 and resource ('Start a persistent process/REPL') and even names return values (PID, initial output, state). However it does nothing to distinguish itself from the near-identical sibling 'process_start', leaving an agent unsure which of the two to pick.

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?

There is no when-to-use guidance, no exclusion of alternatives, and no mention of the lifecycle it implies (that the process later needs read_process_output/interact_with_process and termination via kill_process/force_terminate). The agent must infer all routing from sibling names alone.

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