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

Annotations only declare non-readOnly, non-idempotent, non-destructive; the description goes well beyond that with 'every call files a new request, so never resubmit a pending one', which is the practical consequence of idempotentHint=false. It also enumerates the three outcomes with their side effects: approved means retry the action now, pending means Control Plane review plus an email and Console notification, denied comes with a reason. That is real behavioral disclosure an agent cannot get from 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?

The action and trigger are front-loaded, and nearly every clause carries distinct information (error mapping, gvc requirement, no-resubmit, outcome semantics, out-of-scope routes). It is on the long side for a four-parameter tool and the outcome enumeration could be tightened, but there is no filler 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, yet the description still summarizes the return (request id plus status) and explains what each status means for the caller's next step, which is the part an agent actually needs. Combined with the trigger conditions, missing-input rule, per-GVC requirement, and the pointer to Control Plane support, nothing needed to invoke this correctly is absent.

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 baseline is 3, and the description adds genuine meaning on top: quota values are derived from the error message, cpu-per-workload is in millicores and memory-per-workload in MiB, and gvc is required only for the three per-GVC quota families it names. It stops short of explaining the org parameter or the 0-1,000,000 bound, leaving a little on the table.

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 opening sentence states a specific verb and resource: 'Ask Control Plane to raise an org quota.' It then distinguishes this tool from the adjacent support route by naming exactly what is out of scope (lowering a max, orgs-per-billing-account). An agent can tell this apart from every sibling in the list without opening the schema.

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 trigger condition is explicit and operational: use it after a create or update fails on a quota, with the mapping from error text to quota name ('a workload's total CPU or memory error means cpu-per-workload or memory-per-workload'). It also states the when-not ('file it only when the user wants the increase') and the exclusion (lowering a max and orgs-per-billing-account go through Control Plane support), plus a missing-input rule for requestedMax.

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