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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real context beyond them: result ordering (newest first), the fact that all states are returned so terminated pods appear too, and the pagination rule that the cursor is opaque and single-use for the next call only. What it does not disclose is what happens when results are exhausted or how large a full scan can get.

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 short sentences, scope stated first and the pagination constraint second, with no filler. It is arguably over-terse for the cursor semantics, but every sentence carries information and nothing is redundant.

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?

An output schema exists, so return-value explanation is not owed, and the low-complexity two-parameter read is mostly covered by the ordering and cursor notes. Gaps remain around pagination termination and the fact that no state filtering is possible despite 'every state' being a notable choice, plus the cursor naming mismatch.

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 50%: 'limit' is already documented as 1-200 with default 50, so the description rightly omits it. It does add meaning for the undocumented cursor parameter by explaining opacity and single-use chaining, but it calls it `next_cursor` while the schema property is `cursor`, which risks the agent trying to pass an unrecognized key.

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 the resource and scope precisely: 'Your GPU pods, newest first, every state' tells the agent it returns the caller's own pods (not providers or sandboxes), sorted newest-first, unfiltered by state. It lacks an explicit verb, but the resource plus ownership scope makes purpose identifiable without opening the schema.

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 no when-to-use statement and no alternative named. The agent is left to infer that this is the discovery step before rent_create_gpu_pod or rent_terminate_gpu_pod, and nothing says when a different listing tool should be used instead.

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