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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered; the description adds genuinely new context about required billing write scope and the workspace-claim gate with its 403 failure mode. It does not explain what 'destructive' means here (e.g. whether metadata is merged or replaced), which is the main remaining gap.

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, zero filler: purpose and required inputs first, then credential scope, then the workspace gate and its error. Each sentence contributes a distinct, actionable fact.

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?

For a 6-parameter partial-update tool with full schema coverage, annotations covering mutability/idempotency, and no output schema, the description covers purpose, required inputs, auth, and the most likely failure mode. Nothing needed to invoke it correctly is missing.

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 field meanings are already documented; however, the description adds a constraint the schema does not encode — the schema requires only invoice_id, while the tool actually needs at least one mutable field — which is real semantic value beyond the schema.

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?

States a specific verb and resource ('Change an invoice') and immediately enumerates the mutable fields plus the 'at least one of' rule, so it is clearly distinguishable from create_invoice, delete_invoice, get_invoice, and send_invoice in the sibling list.

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?

Gives the concrete precondition for a valid call ('pass invoice_id and at least one of status, amount, currency, due_date and metadata') and spells out both credential and workspace prerequisites, including the 403 outcome for unclaimed sandbox keys. It stops short of naming alternatives — e.g. whether send_invoice should be used instead to move an invoice to 'sent'.

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