exec

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

With no annotations, the description carries full burden. It discloses that output is combined stdout+stderr, but does not mention error handling, timeouts, permissions, or the `bash -c` execution context (though that appears in the schema). Additional behavioral details (e.g., side effects, safety) are missing.

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 two sentences long, front-loaded with purpose and examples. Every sentence adds value: first for definition, second for usage context. No wasted words.

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?

Given the absence of output schema, the description explains the return format. It covers main use cases (CLI tools). However, it lacks details on working directory, environment, or exit codes, but is sufficient for basic usage with sibling tools.

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 100% with both parameters described ('Sandbox id', 'Shell command to run (executed via bash -c)'). The description adds no parameter-specific detail beyond the schema, so 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?

The description clearly states the tool's purpose: 'Run a shell command inside the sandbox.' It specifies the verb (run), resource (sandbox), and return format (combined stdout+stderr). The examples of CLI tools differentiate it from sibling tools like browser or file operations.

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 description explicitly says 'Use for any CLI work: git, npm, pip, apt, curl, etc.' which provides clear guidance on when to use. It does not mention when not to use or list alternatives, but the examples cover common cases.

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