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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description is not burdened with the full safety profile. It adds useful context that the tool returns the current version and saved fields and explicitly does not reprocess the source, though it omits error behavior and permission requirements.

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 description is two concise sentences with the core action and scope front-loaded. Every sentence adds useful information without repetition or 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?

For a simple single-parameter read tool with rich annotations, the description adequately states what is returned ('current version and saved fields') and what the tool does not do. It is still incomplete about how to obtain the required invoice_id and how invalid IDs are handled.

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%, so the description must compensate for the undocumented invoice_id parameter. It only implies that an invoice was previously found and does not explain that the input is a UUID, where to obtain it, or what happens for an unknown ID.

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 ('Read') and resource ('invoice') and adds scope: a previously found invoice in the connected workspace, with current version and saved fields. It distinguishes itself from reprocessing the source, though it does not name sibling tools such as search_invoices or extract_invoice_data.

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 'previously found invoice' clearly implies this is for retrieval after an invoice has already been located, and 'Does not process the source again' gives an explicit exclusion against re-extraction. However, it does not name the specific alternative tools or state prerequisites such as how to obtain the invoice ID.

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