notion_download_file

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does so effectively by explaining storage locations (FILES_DIR, shared mount), the 24h TTL for shared, Drive upload behavior, and MCP response size limits for base64. It also notes that bytes never traverse MCP parameters in the shared flow, which is valuable operational context. It omits specifics like authentication or error semantics, but given the richness of what is disclosed, this is above average.

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 longer than average but well-structured with a bulleted list and a clearly separated cross-MCP workflow. Each sentence adds necessary information, and the most important purpose is front-loaded. It could be slightly tighter by moving the cross-MCP example into a 'Use cases' subsection, but it remains efficient and scannable.

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?

Despite having no annotations and minimal schema, the description covers all essential operational aspects: destinations, filename handling, storage paths, TTL, size constraints, and an end-to-end email attachment flow. It also gives a pointer to the sibling tool needed to locate block IDs. With an output schema present, return-value details are not needed from the description, and nothing critical is missing.

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 0%, so the description must fully document parameters. It explains destination as an enum with per-value behavior, filename as an override, and that local filenames may include subdirectories that are auto-created. block_id is implied by the opening sentence and the pointer to notion_list_files_on_page. This fully compensates for the sparse schema.

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 opens with a specific verb+resource+scope: 'Download a file from a Notion file/image/pdf/video/audio block.' This clearly distinguishes the tool from siblings like notion_extract_file_text or notion_render_file_page, and the destination options are enumerated. It also cross-references notion_list_files_on_page for finding block IDs, reinforcing its unique role.

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?

The description provides detailed guidance on when to use each destination option (local, shared, drive, base64), including TTL and size constraints. It also includes a step-by-step cross-MCP transfer example to Gmail. However, it does not explicitly contrast this tool with sibling tools that might also retrieve file content (e.g., notion_extract_file_text or notion_render_file_page), so exclusionary guidance is implicit rather than explicit.

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