process_start

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

Annotations already declare destructiveHint=true, non-idempotent, non-read-only, and this description's 'without waiting' adds genuinely new async behavior context. However, it does not disclose consequences (e.g., that starting a command spawns a persistent process/session requiring later process_kill), nor any resource or permission notes.

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?

One tight sentence that front-loads the action and the key behavioral differentiator ('without waiting'). No filler.

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?

Covers the core async behavior and return value, but a mutation tool that spawns persistent OS processes ought to mention that the resulting process must be managed (process_kill) and clarify cwd/shell semantics. Given no output schema and zero param coverage, more disclosure is warranted.

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 0%. The description only explains the required 'command' implicitly, and provides no meaning for 'cwd' (working directory) or 'shell' (shell selection). With three parameters undocumented in both schema and description, the tool relies entirely on param-name inference.

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 action and resource: 'Start a ... command' and states the key outcome 'return a sessionId without waiting'. This clearly distinguishes it from 'exec' (synchronous execution) and from process_read/process_input/process_kill which operate on an already-started session.

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 'long-running or interactive' indicates the use case well, but no explicit exclusion of 'exec' or mention of following up with process_input/process_read. For a session-oriented tool this is clear context without full routing guidance.

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