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

Beyond the annotations (idempotentHint=true, readOnlyHint=false), the description adds crucial behavior: idempotent get-or-create semantics, persistence across stop/start, that parameters (vcpus, disk_gb, ssh_keys, memory_mb) are ignored if the machine already exists, and that disk_gb is fixed at creation. It also explains ssh key security implications and scope needs, giving the agent a clear safety profile.

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 compact (three sentences) and front-loaded with the core purpose. It provides valuable distinctions (sandbox, delete) without redundancy. Every sentence earns its place: purpose, idempotency, persistence. No filler or repetition of schema details.

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 rich schema (100% coverage) and clear annotations, the description covers all critical behavioral aspects: idempotency, persistence, and parameter-ignore semantics. It does not explicitly describe return values, but with no output schema and sibling tools that operate by name, the omission is minor. Slightly more on what the function returns would make it fully complete.

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%, and the schema already provides detailed per-parameter descriptions including constraints, defaults, and 'ignored if already exists' behavior. The tool description adds overall context (idempotency, persistence) but does not significantly enhance parameter-specific understanding beyond what the schema provides, 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 uses a specific verb+resource: 'Get or create a persistent Linux machine by name.' It clearly distinguishes from siblings by contrasting with sandbox ('Unlike a sandbox, the disk survives stop/start') and referencing scalix_computer_delete as the only erasure path, which separates it from compute lifecycle tools.

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?

Explicitly states when to use: when a persistent machine is needed, and contrasts with sandbox. It advises that retrying is safe due to idempotency, and gives specific guidance on ssh_keys ('Only needed if a human will ssh in... exec, write_file and read_file all work without one') and scope requirements. It also points to scalix_computer_set_ssh_keys for changing keys, providing an alternative.

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