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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: result ordering is newest-first and terminated/failed sandboxes are hidden unless explicitly requested. It does not mention pagination limits beyond the cursor note or how many pages exist.

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 short clauses, front-loaded with scope and ordering, then default filtering, then cursor handling. No sentence is wasted and nothing requires re-reading.

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?

With an output schema present, the description need not explain return values, and it correctly spends its words on ordering, default filtering, and cursor reuse. The only real gap is that `cursor` versus `next_cursor` naming is left ambiguous for a caller building a follow-up request.

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 33%, so the description carries real weight and does explain the `state` filter's default semantics, which the schema does not. However it refers to `next_cursor` while the input property is named `cursor`, leaving the input parameter's purpose to be inferred, and `limit` gets no mention beyond the schema. Partial compensation, not full.

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?

"Your sandboxes, newest first" states the resource and ordering specifically and distinguishes it from the single-resource sibling rent_get_sandbox by implication. It stops short of naming an alternative explicitly, so it is clear but not sibling-differentiated on the page.

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 default state filter ("every state but terminated and failed; `state` picks one") tells an agent when the default view suffices and when to narrow, which is real usage guidance. It never says when to prefer this over rent_list_gpu_pods or rent_get_sandbox, so the alternative-selection guidance is only implied.

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