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

Annotations already convey destructiveHint=true and idempotentHint=true; the description adds two useful behavioral specifics beyond that — cancellation applies only to queued/running eligible assessments, and the operation reconciles refundable reserved credit. It does not contradict the annotations.

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?

A single sentence front-loads the primary action and packs in eligibility scope plus the credit side effect without waste. Every clause earns its place, and it is appropriately sized for an action tool.

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?

The description covers the core action, state constraints, and the credit side effect, but with no output schema it leaves success/error return behavior unexplained, and it never addresses the three required parameters — especially idempotencyKey, which is mandatory. 'Eligible' is also left undefined. Adequate but with clear gaps.

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 only 33%, with assessmentId and idempotencyKey left undoced in the schema. The tool description does not compensate: it never explains how to obtain assessmentId or how to generate and use idempotencyKey. The required idempotencyKey parameter in particular has zero guidance.

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 uses a specific verb ('cancel') and resource ('assessment'), and adds state scope ('queued or running') plus the credit-reconciliation side effect. The action is clearly distinct from sibling tools like launch_assessment, prepare_assessment, get_assessment, and list_assessments.

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 phrase 'eligible queued or running' gives implied context that completed assessments are not valid targets, but the description never explicitly states when to use this tool versus alternatives or suggests checking status first via get_assessment. No exclusion or alternative-routing guidance is provided.

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