start-process

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

With no annotations, the description carries full burden. It discloses that stdout/stderr are not captured and warns about lingering background processes. However, it fails to disclose whether the tool blocks, its return value, error handling, or termination behavior.

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?

Two sentences: the first states the core purpose, the second adds critical warnings. No fluff or redundancy. Front-loaded with the essential action.

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?

The description is too sparse for a tool with 5 parameters, no output schema, and no annotations. It omits parameter meanings, return value, synchronization model, and lifecycle management. The warning is helpful but insufficient for complete agent understanding.

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%, so the description must add meaning. It does not describe any of the 5 parameters (script, name, args, cwd, envs) beyond the schema. The warning mentions stdout/stderr but not how parameters relate to that behavior.

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 clearly states 'Start a new process' with the verb 'Start' and resource 'process'. It distinguishes from siblings like 'allow-start-process' and 'delete-process' by being the actual execution action. However, it doesn't specify whether the process runs synchronously or asynchronously.

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 warning explicitly advises against invoking background processes that won't exit automatically and notes that stdout/stderr will not be captured, providing clear usage context and exclusions. It does not name alternative tools, but the context is sufficient for an agent to decide when to avoid this tool.

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