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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real beyond-annotation context: download URLs changed for security reasons and expire, plus an auth requirement (API key with access to this app). That is meaningful behavioral disclosure an agent needs before acting.

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 core constraint (expiring link) is front-loaded and worthwhile, but there is redundancy: 'Get a download link for the invoice PDF' is immediately restated as 'Returns a link to the invoice PDF,' and the brand prefix repeats the title. The content is sound but not tightly trimmed.

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 read-only, two-param tool with no output schema, the description covers the essentials: what it returns (a link), the critical time-sensitivity of that link, and the auth requirement. Nothing important about correct invocation is missing, though it could note the link's destination format.

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 both parameters (company_id, invoice_id) are already fully documented in the schema. The description adds no format, sourcing, or constraint detail about them, 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?

The description uses a specific verb and resource ('Get a download link for the invoice PDF') and clarifies that it returns a link rather than the PDF itself, which usefully distinguishes it from a plain invoice-fetch tool. It does not explicitly name the sibling it differs from (e.g., get_invoice), so it stops short of full sibling differentiation.

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?

It gives one concrete usage rule ('fetch the link right before you use it') tied to URL expiry, which is genuinely helpful. However, it never states when to choose this tool over get_invoice or another document-download sibling, so guidance is implied rather than explicit.

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