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

With no annotations, the description carries the full burden and does well: it discloses the conditional early-return shape (needs_selection plus previews with title and preview_id) and the success shape (pdf_url). It omits side effects — whether a PDF is persisted or overwritten, and any auth/cost considerations.

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?

Three tight sentences, front-loaded with purpose then the branching call sequence. Every clause is functional — no restatement of the title 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?

No output schema exists, and the description compensates by naming both response shapes (selection payload and pdf_url). For a 2-param, all-optional tool with zero annotations it is nearly complete; only failure/error behavior and persistence semantics are unaddressed.

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 are already documented, including the meaning of omitting preview_id. The description reinforces the no-arg branch but adds no syntax or format detail beyond the schema; notification_message is untouched in the description.

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: 'Generate a PDF from a preview.' The preview linkage implicitly separates it from list_previews/get_preview, but it never names a sibling or explicitly contrasts with them, leaving differentiation to inference.

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?

Gives explicit operational guidance: call with no args first, handle the needs_selection branch by asking the user, then re-call with preview_id — and the single-preview case resolves immediately. It covers how to drive the tool but offers no guidance on prerequisites (e.g., that preview_document must have run) or when to prefer list_previews instead.

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