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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds real operational context not in structured data: the whole cluster stops on completion or cancel, billing continues during preparation, and SSH must be started locally with emt_cluster.py. That lifecycle and billing behavior is exactly the kind of thing an agent needs before calling a destructive tool.

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?

Three tightly packed sentences, front-loaded with purpose then the two operational gotchas. No filler or restatement of the tool name.

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?

The workflow-critical warnings (local SSH launch, cluster teardown, ongoing billing) are covered, which matters for a destructive tool, but with 12 undocumented parameters, a nested experiment union, and no output schema, an agent still lacks enough to fill the request 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 12 parameters, including nested objects and a three-way experiment union, yet the description explains none of them. It only hints obliquely at the ssh parameter ('your private key') and never addresses experiment kinds, level, maxMinutes, clusterOrder, or the required idempotency_key, so it fails to compensate for the documentation gap.

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?

Names a specific verb and resource: 'Attach work to an already rented dedicated 2–4-node cluster.' The 'already rented' qualifier implicitly separates it from emt_rent_cluster and emt_start_experiment, though no sibling is named explicitly.

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 precondition (cluster must already be rented) is clear, and the description explicitly states one important limitation: it does NOT start SSH remotely. It stops short of naming emt_rent_cluster or emt_start_experiment as alternatives, so the routing is inferred rather than stated.

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