List all stored PDF drafts in this session. Returns previews[{preview_id, title}], count, and most_recent_preview_id. Use when the user taps List PDFs or asks which drafts exist. Does not show document body — follow with get_preview after they pick.
| Name | Required | Description | Default |
|---|---|---|---|
| notification_message | No | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Changes observed during successful MCP inspections.
Input schema / requiredPrevious value: -[
- "notification_message"
-]New value: +[]Input schema / properties / notification_message / descriptionPrevious value: -"Short user-facing sentence for this action. Use {{var}} placeholders that replay will fill from API results (e.g. Added ₦{{money_delta}}. Balance ₦{{money_after}}.). Shown to the user if the follow-up reply fails."New value: +"Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."Input schema / properties / notification_messageAdded value: +{
+ "description": "Short user-facing sentence for this action. Use {{var}} placeholders that replay will fill from API results (e.g. Added ₦{{money_delta}}. Balance ₦{{money_after}}.). Shown to the user if the follow-up reply fails.",
+ "type": "string"
+}Input schema / requiredPrevious value: -[]New value: +[
+ "notification_message"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does well: it discloses the session-scoped nature, the concrete return shape, and critically what is NOT returned (document body). It stops short of stating read-only safety or any permission/rate-limit behavior, which leaves a small gap for a tool with zero annotation coverage.
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 return shape, then usage. No redundant restatement of title or name and no 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?
There is no output schema, but the description enumerates the returned fields (previews, count, most_recent_preview_id) and the follow-up flow, so an agent has everything needed to call it and act on the result.
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% for the single notification_message parameter, so the schema already carries its meaning; the baseline of 3 applies. The description adds no param-level detail, which is acceptable given the coverage.
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 (List) and resource (stored PDF drafts) with explicit scope (this session), and even names the return payload. An agent can distinguish it from pdf__get_preview and pdf__delete_preview without opening any 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?
Gives explicit triggering conditions ('user taps List PDFs or asks which drafts exist') and an explicit boundary plus next step ('Does not show document body — follow with get_preview after they pick'). This is exactly the routing guidance an agent needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.