start_process

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the executable is allowlisted, the session is bounded, and it runs with the user's account privileges, but it omits session lifecycle details such as how output is retrieved, whether the process persists, and cleanup 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?

The definition is only two sentences and front-loads the core action. The privilege note is useful, though the wording is slightly awkward and the description could better structure the key constraints.

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 4-parameter process-start tool with no annotations, no output schema, and 0% parameter description coverage, the description is too thin. It should explain session identity/return value, output retrieval, timeout behavior, and how this differs from run_command.

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% across four parameters. The description hints at the executable allowlist and bounded timeout behavior, but provides no meaning for cwd, args, timeoutMs, or how the parameters interact.

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 uses a clear verb+resource phrase, 'Start an allowlisted bounded process session,' so the agent knows this initiates a process session. It adds useful qualifiers ('allowlisted', 'bounded', user-account privileges), but does not explicitly distinguish this from the sibling run_command tool.

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 explicit guidance on when to use this tool versus run_command, list_processes, or read_process_output. The description implies it is for allowlisted persistent sessions, but an agent must infer that context and the exclusions.

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