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

Goes well beyond the annotations by disclosing the billing model (billed hourly on your own key, no rent.dev balance consumed), the pod id's lifetime, strict argument validation ("arguments not listed are refused by name"), and the concrete failure contract for capacity exhaustion (503, no_capacity, retry_after, pod recorded as failed). These are exactly the operational facts an agent needs that readOnlyHint/openWorldHint/destructiveHint do not convey.

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?

Front-loads the action and vendor, then builds outward to billing, lifecycle, validation, and error handling with almost no filler. Density is high and the parenthetical/backtick styling makes it slightly harder to scan than plain prose, but every clause carries distinct information.

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 9-parameter, open-world creation tool with a mutation and cost implication, the description covers credentials, billing, id lifetime, validation strictness, and the main failure mode. Return values are covered by the existing output schema, so nothing essential is left for the agent to guess.

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 already 89%, so the schema carries most parameter documentation. The description still adds value by pointing to rent_quote as the source of valid gpu_type values, which is a discovery hint the schema's example alone does not provide, and by warning that unlisted arguments are rejected rather than ignored.

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 ("Starts a GPU pod on RunPod") plus the defining constraint that it uses the caller's own RunPod key rather than a rent.dev balance, which is exactly what separates it from the sandbox-creation sibling. An agent can classify the tool 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?

Gives an explicit prerequisite (store the key first via rent_set_byok_credential, vendor runpod), an explicit lifecycle counterpart (RunPod bills hourly until rent_terminate_gpu_pod), and an explicit recovery path on 503 no_capacity: retry after retry_after or select another GPU type from rent_quote. It stops short of naming when NOT to use it (e.g. non-GPU workloads that belong to rent_create_sandbox), so it is strong but not exhaustive.

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