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

With no annotations, the description carries the full burden and does well: it discloses the sandbox lifecycle ('created for the job and stopped right after, so nothing idles on your bill'), the exact return shape (exit code plus last 16 KB of stdout/stderr), and the non-secret constraint on env vars. It stops short of stating auth/key prerequisites for provider selection or what happens on timeout or failure.

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 core capability, lifecycle and return values are front-loaded and tight, but the trailing sentence 'Free watch-only logs would_offload and runs nothing' is incoherent and fails to earn its place, diluting an otherwise efficient description.

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 an 8-parameter tool with nested file objects and no output schema, the description supplies the missing return-value information (exit code, truncated stdout/stderr), the sandbox lifecycle and provider defaults. It is nearly complete, lacking only failure/timeout behavior and provider-key prerequisites.

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 the schema already documents cmd, env, files, runtime, provider, template, timeout_s and free_mb. The description adds only marginal meaning ('Send small input files with it', the non-secret qualifier on env), 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?

States a specific verb+resource (run a shell command) plus the execution environment (fresh cloud sandbox on the caller's own provider account) and enumerates the concrete providers. Nothing in the sibling set (provider keys, memory, reports) overlaps with this, so an agent can identify it immediately.

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?

Usage is only implied: 'Send small input files with it' hints at the input-files use case, and 'Free watch-only logs would_offload and runs nothing' gestures at a when-not boundary but is garbled and names no real sibling tool. There is no explicit guidance on when to prefer this over any alternative.

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