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

Goes well beyond the annotations by disclosing the financial side effect ('Spends money from your Lium balance'), per-second billing that continues while idle until remove_pod, and the mandatory idempotency key with its 24-hour retry window. These are exactly the high-stakes traits an agent needs before making an irreversible purchase.

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?

One dense paragraph that front-loads the action, then cost, then parameter modes, then the idempotency contract. No filler sentences; every clause carries operational weight.

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 no output schema, the description still names the return values (pod id, ssh command), covers cost, billing duration, idempotent retry, and both parameter modes. Nothing material to a correct invocation 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%, so baseline is 3, but the description adds real meaning: it explains the gpu-mode vs node_id-mode split and that country and max_price_per_gpu_hour only apply with gpu, not node_id. It omits mode guidance for template_id, name, and ssh_public_key, which are left to the schema.

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 ('Rent a GPU pod on Lium'), the blocking behavior ('wait until it runs'), and the return payload ('pod id and the ssh command'). It is clearly distinguishable from siblings like remove_pod, list_pods, and search_gpus.

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?

Explicitly gives two mutually exclusive invocation paths ('give gpu ... or node_id from search_gpus alone'), routes the agent to sibling tools (search_gpus, list_templates), and prescribes the retry protocol with idempotency_key on failure/timeout. The when-to-use conditions are stated rather than inferred.

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