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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds real value beyond that by disclosing result volatility ('offers change as capacity moves'), the community-host exclusion default, and the meaning of nodes_available being null ('only a launch can tell'). Solid but it does not cover pagination or result-set size limits.

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?

Purpose and the create_cluster dependency are front-loaded in the first two sentences, and every subsequent clause carries information. It loses a point for being a single dense paragraph blending selection guidance with a long enumeration of returned offer fields, which is harder to scan than a short structured list.

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 carries the burden of describing the returned offer object, and it does so field by field (offer_id, location, interconnect, deployment_type, host_tier, supported stacks, min_nodes/max_nodes, allowed_node_counts, nodes_available, node specs, both rates). For a 9-parameter tool with zero required parameters, an agent has everything needed to call it and interpret the result.

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 description coverage is 100%, so the baseline is 3; the description earns above that by explaining the pricing model semantics that the schema only implies: hourly_rate_per_node is one machine while hourly_rate is the whole cluster at node_count machines, and nodes therefore changes the quoted rate. It also explains why gpus_per_node is worth leaving out and ties volume to storage_id, which the schema description states only tersely.

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: 'Find the machines a multi-node GPU cluster can be created on right now.' It explicitly distinguishes itself from the neighbouring create_cluster by noting that create_cluster needs an offer_id from here, and from list_gpu_types by framing offers as whole machines rather than GPU SKUs.

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 concrete when-to-use guidance ('create_cluster needs an offer_id from here'), a workflow prerequisite ('Show the user the location, interconnect, GPUs per machine and hourly_rate with the per-machine price before creating'), and a freshness caveat ('Offers change as capacity moves, so use a fresh one'). It also explains the two behaviour-changing flags: include_community defaults off, and volume should be true when a storage_id will be attached.

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