compare_compute_inventory

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

No annotations, so description carries full burden. It discloses independent sizing, multiplication, optional storage cost, and output structure (per-row, totals, cheapest). Does not mention that it's read-only (cost estimate) but given context it's implied. No contradictions.

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 sentences: purpose, mechanics, outputs and use case. No filler, front-loaded, every sentence adds value.

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?

No output schema, but description covers return values (per-row, per-cloud totals, cheapest). Also explains optional disk cost. Could mention limits or performance for large lists, but adequate for typical use.

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 0% for top-level parameter (workloads array), but description explains that workloads are a list of rows with vCPU/memory specs, quantity, hours, and optional disk. Adds meaning beyond schema's field descriptions, especially the 'cheapest VM' logic and per-row matching.

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?

Description clearly states bulk comparison of compute workloads across AWS, Azure, GCP, with specific mechanic (cheapest VM per spec) and output structure. Distinguishes from siblings like compare_workload (single) and compare_storage_inventory (different resource type).

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 says useful for sizing-sheet style inputs, implying batch comparison context. Does not specify when to avoid or mention alternatives like compare_workload for single workloads, but context is clear enough.

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