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

Annotations already flag destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely new behavioral context: the required account-bound computer:write OAuth scope, the prompted local owner approval, and that a process ID is returned. It does not describe output streaming or how the process lifecycle is managed, which keeps it below a 5.

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 tightly packed sentences with zero filler; the scope/approval qualifier is front-loaded and the sibling alternative follows immediately. Every clause carries information an agent needs before calling.

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?

With no output schema, the description still signals that a process ID is produced, and the sibling set (read_interactive_process_output, send_interactive_process_input, stop_interactive_process) makes the follow-up path inferable. Auth and approval requirements are covered; only return format and streaming behavior remain unstated, which is a minor gap for a destructive open-world tool.

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 both parameters (command and maxMinutes) are fully documented in the schema, including the server-enforced duration limit. The description adds no syntax, quoting, or format guidance beyond that, so the baseline 3 is appropriate.

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?

States a specific verb and resource: 'Start an interactive EXZA-owned shell process (with ID)', and notes the approval precondition. It explicitly separates itself from exza_start_background_job, though it does not distinguish itself from the nearby exza_run_shell_command sibling, which an agent could easily confuse with this one.

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?

Gives an explicit routing rule: 'For detached monitored jobs use exza_start_background_job instead.' That is a clear when-not-to-use with a named alternative. It stops short of covering the other obvious alternative (exza_run_shell_command) for one-shot commands, so the guidance is not exhaustive.

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