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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds that results are scoped to the signed-in freelancer (an auth/ownership constraint) plus the downstream-id workflow, but says nothing about pagination or result-set size despite the offset parameter.

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 short sentences, front-loaded with the action and scope, followed by the follow-up step and the anti-pattern warning. No filler.

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 presence of an output schema means return values need not be described, and the list-then-read workflow is covered. However, for a paginated list tool with an undocumented offset parameter, the omission of any pagination guidance leaves a real gap.

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% and the single parameter is offset, which the description never mentions. With a low-coverage schema the description is expected to compensate, and it does not explain pagination, defaults, or how many invoices come back.

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 with scope ('the signed-in freelancer's invoices'), which both identifies the operation and distinguishes it from read_invoice and the other invoice-mutation siblings.

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?

'Use a returned id with read_invoice. Do not guess an invoice.' gives a clear workflow: list first to obtain ids, then read. It routes to the correct sibling and rules out guessing, though it never states when listing is unnecessary (e.g., if you already hold an id).

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