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

Annotations already cover the read-only, non-destructive safety profile, but the description adds real value beyond them: output is base64 with file name and size, the document is returned 'as issued' (immutable snapshot), and it names an auth requirement ('Needs the user's Cotlet API key with access to this app'). The 'does not change or send' clause partly restates readOnlyHint, keeping it from a 5.

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?

Front-loaded and informative, but wastes space: 'base64 encoded' appears twice in back-to-back sentences, and the first two sentences largely restate each other. It is functional rather than tight.

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?

With no output schema, the description carries the return-format burden and does explain the payload (base64 PDF, file name, size) plus the auth prerequisite. It is complete enough to call correctly, missing only pagination/size limits or error behavior for a missing invoice.

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 100%, so the single invoice_number parameter is already fully documented (including its source, list_invoices). The description adds no format or syntax detail beyond the schema, so 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?

States a specific verb and resource (get the invoice PDF) and clarifies scope: 'Returns the PDF copy of one issued invoice, base64 encoded, with its file name and size.' This cleanly distinguishes it from sibling metadata/list operations like get_invoice and list_invoices without opening a 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?

'Use it to attach the invoice to an email or save it to storage' gives clear intended use, and 'it does not change the invoice or send anything' implicitly routes away from mutation/send tools. However, it never explicitly names the alternative (e.g., get_invoice for metadata) or states a when-not condition, so it stops short of full routing guidance.

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