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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context: all examples are fictional, no live GPU quotes are supplied, no automatic benchmarking or reservation occurs, and parameters are processed without persistence. This goes beyond the annotations and helps set accurate expectations.

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?

The description is four sentences and front-loads the core purpose before adding exclusions and input-source guidance. Each sentence adds distinct information, though the list of negations could be slightly tighter. Overall it is appropriately sized for the tool's complexity.

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?

Given the rich input schema, output schema, and annotations, the description covers the essential context: what the tool compares, what it filters, what it does not do, and where to get exact inputs. It does not need to explain return values because an output schema exists. The only minor gap is not explicitly stating when to prefer this over sibling cost-planning tools, but the exclusions largely compensate.

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 the schema already documents each parameter. The description adds semantic meaning by explaining that compute, setup, storage, and egress costs are combined 'per accepted output,' and that mismatched workload labels, currencies, quality, and memory limits are filtered. This clarifies how the parameters relate to each other beyond their individual schema descriptions.

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?

The description names a specific verb ('compares measured workload runs') and a specific resource (compute costs) with the exact cost components considered. It also distinguishes itself from siblings by explicitly negating live GPU quotes, inventory, benchmarking, reservation, and infrastructure management, making its scope unambiguous.

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?

The description gives clear context for when to use the tool: comparing entered workload runs rather than obtaining live data. It also provides a concrete instruction to 'Retrieve compute with fetch or read its example resource to obtain exact inputs,' which routes the agent to the correct data source. It does not explicitly name sibling tools as alternatives, but the exclusions effectively communicate what this tool is not for.

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