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

The read-only annotations already establish safety, and the description adds meaningful behavioral detail: results are limited to authorized invoices and certain sensitive/display fields are intentionally absent. It does not describe error behavior or auth failure modes, but for a simple read-by-ID tool with safety annotations this is a small 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?

A single sentence earns its place: it names the action and resource, states the available fields, and lists exclusions. No filler or redundancy.

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 simple one-parameter read tool with read-only annotations, the description gives enough shape of the response by listing the field groups and exclusions. There is no output schema, but the high-level return contract is clear; the main omission is explicit confirmation that invoice_id is required.

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?

The single parameter is fully documented by the schema ('Invoice ID returned by search-invoices'), so the description adds no extra parameter-level meaning. With 100% schema coverage, the baseline 3 applies.

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 opens with a specific verb and resource ('Returns one authorized invoice') and then narrows the contract by naming the included field groups and the excluded ones. This makes it easy to distinguish from siblings like search-invoices (list vs. one) and preview-invoice (bounded vs. excluded fields).

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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as the alternative for excluded fields such as payment links or addresses. The usage context is only implied by 'one authorized invoice' and by the schema note that invoice_id comes from search-invoices, which is adequate but leaves routing decisions to the agent.

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