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

Beyond the annotations (destructiveHint=true, idempotentHint=true, readOnlyHint=false), the description adds real behavioral value: work already performed still incurs credits and final usage/refunds only appear after settlement. This is exactly the kind of cost/settlement context annotations cannot convey, though it omits auth or timing details.

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?

Two tight sentences with zero waste and the consequence front-loaded after the action. Only minor weakness is that the opening sentence is thin relative to the useful second sentence.

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?

An output schema exists so return values need not be explained, and the key concern for a cancellation tool — cost/refund implications — is covered. However, with three undocumented required parameters and no usage context, it is only minimally complete for a destructive, idempotent-keyed operation.

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 0% across three required parameters (brandId, runId, idempotencyKey) and the description supplies no meaning for any of them. Notably idempotencyKey is never mentioned even though the annotation flags idempotency, so the description fails to compensate for the coverage gap.

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 sentence 'Request cancellation' essentially restates the tool name without naming the resource being cancelled (a research run) or distinguishing it from near siblings like cancel_post or pause_research_schedule. An agent gets the action but not the object or the boundary against similar tools.

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?

No when-to-use guidance is given and no alternative is named. The credits/refund note hints at a caution, but there is no explicit condition telling the agent when to cancel versus pause a schedule or when not to cancel at all.

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