process_start

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses lifecycle semantics (kept alive across MCP tool calls) and the processId handoff to process_read/write/kill, but omits permissions/auth requirements, concurrency limits, timeout or failure behavior, and interaction model details.

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, zero waste: purpose and persistence first, then the return value/handoff, then the exclusion and alternative. Front-loaded and well ordered.

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 3-param tool with no output schema, the description covers purpose, return value, and the key sibling routing, which is nearly everything an agent needs. It falls short only on permissions and failure/timeout behavior, which are not otherwise documented.

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 command, cwd, and env. The description adds no parameter-level syntax or defaults beyond what the schema states, so the baseline 3 applies.

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 names a specific verb and resource (start a long-running or interactive non-agent shell command) with crisp scope qualifiers. It distinguishes itself from process_read/write/kill (via the returned processId) and from agent_start (via the non-agent exclusion), so an agent can select it without opening any schema.

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 gives an explicit when-not rule: do not use for Codex, Antigravity CLI (agy), or Claude Code agent work, and names the alternative (agent_start) with the reason (dedicated parallel workspaces, survives lifecycle changes). The use case is unambiguous.

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