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 return shape ('deleted true/false'), the scope limit (this session only), the non-effect on already-generated public files, and an input safety rule ('Never accept path-like ids'). It omits irreversibility and any permission/auth requirements, which is the remaining gap for a destructive operation.

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 dense sentences, zero filler, with the core action and scope front-loaded and the caveats and safety rule following in priority order. Every sentence carries distinct information.

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 two-parameter delete tool with no output schema and no annotations, the description supplies scope, side effects, return value, and input constraints — everything needed to call it correctly. Return values are covered in prose precisely because no output schema exists.

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 already 100%, so the baseline is 3, but the description adds real meaning: preview_id must come from list_previews/get_preview in THIS session and must never be path-like — a validation constraint not stated in the schema. It says nothing extra about notification_message, hence not a 5.

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 ('Delete one stored PDF draft') scoped precisely by 'preview_id from this chat session only', which separates it from the list/get/generate siblings. The session-only qualifier and the id type make the operation unambiguous.

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?

Provides clear context: agent-only (hidden from suggestion buttons) and session-scoped, and adds an exclusion ('Does not remove already-generated public PDF files') that tells the agent when this is the wrong tool. It does not explicitly name the sibling to use for deleting public PDFs, so it stops short of full when/when-not routing.

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