start_program

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

No annotations provided, so description carries full burden. It only states 'Start a CLI program in a PTY' and returns a pid. Lacks details on side effects, blocking behavior, lifecycle, or interaction model with siblings.

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 description is short and front-loaded. It efficiently states the purpose and parameters. Minor room for improvement: the Args/Returns format adds structure.

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?

Despite low complexity (1 param, no annotations), the description lacks important context such as asynchronous execution, how to stop the process, or output format details. The output schema is said to exist but not visible, so return pid is mentioned but not structured.

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 coverage is 0%, but description adds examples ('cat', 'python -i', 'ls -la') which helps clarify the command parameter. However, no constraints or formatting guidance beyond the examples.

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 the verb 'Start' and resource 'CLI program in a PTY'. It distinguishes from sibling tools like stop_program, read_output, etc., which manage or interact with processes.

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?

No guidance on when to use this tool versus alternatives. No mention of prerequisites, error conditions, or how the started program relates to other tools.

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