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

Annotations already declare destructive, openWorld, non-idempotent and non-readOnly, so the safety profile is covered. The description adds genuinely new context the annotations cannot convey: full-computer scope, required account-bound computer:write OAuth, and a prompted local owner approval step. It still does not mention timeouts or how output/errors are returned, so not 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 dense sentences, no filler, with the scope and the sibling alternative front-loaded before the auth caveat. Every clause carries distinct information.

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 single-parameter destructive execution tool this covers purpose, blast radius, auth and approval prerequisites, and the background alternative. The only missing piece is operational detail on execution limits (timeouts, output capture), which matters for a shell runner.

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?

With one parameter at 100% schema coverage, the schema already explains the command string and its side-effect review obligation. The description adds nothing about the command parameter (no syntax, cwd, shell flavor, or length limits), so it sits at the high-coverage baseline.

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 ("Run one shell command") plus its scope ("full-computer scope"), and explicitly routes longer runs to exza_start_background_job. The agent can distinguish it from the background-job and interactive-process siblings without opening any schema.

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 a clear when-to-use alternative: use exza_start_background_job for longer background runs, and the word "one" implies a single foreground invocation rather than a persistent session. It stops short of naming exza_start_interactive_process as the alternative for persistent/interactive shells, so the exclusion set is incomplete.

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