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

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior: the response is base64 plus a file name, the duplicate variant carries a download date, and access requires a Cotlet API key scoped to this app. That is context beyond the structured fields.

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?

Four short sentences, front-loaded with what is returned. Slightly redundant restatement of 'PDF' and 'base64' across the first two sentences, but nothing is wasted and the duplicate/auth notes earn their place.

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 single-invoice PDF fetch there is no output schema, and the description compensates by describing the return payload (base64 + file name), the duplicate variant, and the access requirement. Minor gaps remain (no size limits or pagination/streaming notes), but an agent has what it needs to call it.

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 coverage is 100% and both parameters are documented in the schema (including invoice_id's origin from list_invoices). The description still adds meaning for 'duplicate' by explaining the consequence of setting it true (the returned file carries the download date), which goes beyond the schema's terse 'true for a duplicate'.

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+resource: retrieve one issued invoice as a PDF. The 'PDF, base64 encoded' framing distinguishes it from the sibling ifirma_get_invoice, which returns structured invoice data rather than a document. An agent can tell what it gets and how it is encoded without opening the 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?

The description implies the use case (fetching the PDF of an issued invoice) and gives the duplicate toggle's context, but it names no alternative and states no when-not conditions. It also cites an access prerequisite (Cotlet API key with app access), which is helpful but not routing guidance.

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