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

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses that this is a delete operation, limited to session drafts, hidden from suggestion buttons, returns a boolean result, and does not affect generated public PDF files. It also adds a concrete safety rule against path-like ids.

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 description is front-loaded with the core action and then adds only high-value constraints. Every sentence contributes scope, behavioral, or parameter-safety information without repetition.

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?

Given the lack of annotations and output schema, the description sufficiently covers the operation's scope, side effects, return value, and id safety constraints. An agent has enough information to invoke this tool correctly without needing additional clarification.

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%, so the schema already documents both parameters. The description adds useful semantic constraints beyond the schema, especially that preview_id must come from this session and must never be path-like; it does not add extra meaning for notification_message.

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 verb and resource: delete one stored PDF draft by preview_id. It also scopes the action to this chat session and distinguishes it from generated public PDF files, which helps differentiate it from sibling tools such as get_preview and list_previews.

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?

It gives clear usage context: this deletes a draft from this chat session only, is agent-only, and must not be used for already-generated public PDF files. It does not explicitly name get_preview or list_previews as alternatives for obtaining the preview_id, though the schema points to them.

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