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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the bar is lower. The description still adds genuinely new behavioral detail: processing happens client-side on dozokit.com ("files never leave their device") and attached conversation files are rejected. "Read-only" merely restates the annotation.

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 purpose and the operation list are front-loaded and each gloss on the enum values earns its place. The closing French sentence and the bare "Read-only" are redundant with the body and the annotations respectively, but the cost is small.

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?

No output schema exists, and the description implies the return value (a link the user follows to dozokit.com) and the privacy model well enough to act on it. Combined with annotations covering safety and the description covering the enum semantics, an agent has everything needed to call it correctly.

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 only 50% — `tool` has no schema description — but the description compensates by glossing every enum value (merge = several PDFs into one, split = by page ranges, organize = reorder/rotate/delete), which is meaning the bare enum names do not carry. `lang` is already documented in the schema, and the trailing French sentence reinforces it.

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 states a specific action (hand the user the Dozo PDF tool at dozokit.com) and enumerates the six supported operations, so the agent knows exactly what this call produces. It does not differentiate itself from the sibling make_invoice, though the PDF domain makes the split obvious.

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?

Usage context is clear: use this when the user needs a PDF operation, and pick the matching value of `tool`. The explicit exclusion — "Files already attached to this conversation cannot be used" — is a real routing constraint that prevents a wrong call. It does not name make_invoice as an alternative, but there is no plausible competition between the two.

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