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

With no annotations, the description carries the full disclosure burden and does so well: it reveals that pausing stops the billing lease (a cost consequence) and that data is archived rather than deleted (a retention consequence). Both go beyond what the tool name alone implies. It stops short of covering idempotency or prerequisite states (e.g., behavior if already paused), but the key operational effects are disclosed.

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?

Two sentences with zero filler: the action and resource lead, followed by the two most decision-relevant consequences (billing, data retention). Every word earns its place and the most important disambiguator ('not deleted') is positioned at the end for emphasis.

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 single-parameter tool with no output schema and no annotations, this is nearly complete: purpose, cost impact, and data fate are all covered. The only gaps are minor — no mention of reversibility via resume_instance and no statement about calling pause on an already-paused instance — but nothing an agent needs to safely invoke the tool is missing.

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%, and the schema already documents the single id parameter with provenance ('as returned by create_instance or list_instances'). The description adds no parameter-level detail beyond 'an instance,' so baseline 3 applies — the schema does the heavy lifting and the description neither conflicts nor adds value here.

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 and resource ('Pause an instance') plus the concrete effects: stopping the instance and its billing lease. The phrase 'Data is archived, not deleted' actively distinguishes it from the destructive sibling delete_instance, so an agent can tell it apart without opening other schemas.

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 implies the decision context — pause when you want to stop compute and billing while preserving data — especially through the contrast 'archived, not deleted.' However, it never explicitly names alternatives like resume_instance (for restarting) or delete_instance (for full removal), so the agent must infer the routing logic.

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