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

Annotations only declare readOnly=false, idempotent=false, destructive=false; the description adds real behavioral context beyond that: a 15-minute aggregate running-credit and capacity requirement, a rejection path tied to unverified templates, and the identity-protection effect of prevent_cloning. The Idempotency-Key retry advice sits in mild tension with idempotentHint=false but is not a direct contradiction, since it concerns caller-side key persistence rather than the tool's own idempotency.

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?

It is short and front-loaded, but the opening sentence is cryptic ('exact body' for what?) and the sentences read as terse notes rather than a coherent definition. No filler, but clarity is sacrificed for brevity.

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 nested-body mutation tool with no output schema and only thin annotations, the description omits what a successful call returns, what a template must be, error/insufficient-credit behavior, and most body fields. The cost and rejection hints are useful but leave the agent short of what it needs to call this correctly.

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 0% across a nested body with seven sub-properties, so the description must carry the load. It explains only require_office_ready, prevent_cloning, and obliquely the idempotency/request_key and the 15-minute auto-stop default, leaving template, name, require_dedicated, auto_stop_minutes, and max_stopped_hourly_usd undefined.

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 never states plainly that this provisions a new machine from a template; it opens with an instruction about persisting an Idempotency-Key and only implies creation via the phrase 'before provisioning' and 'Creation needs 15 minutes...'. An agent must infer the verb+resource from the tool name alone, and no sibling (e.g., machine_request, template_create) is contrasted.

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?

There is a procedural instruction ('Persist a unique Idempotency-Key and exact body before calling') and one conditional ('require_office_ready rejects an unverified template'), but no statement of when to choose this over machine_request or machine_start. The guidance is about caller preconditions rather than tool selection.

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